Search

Neural sequence-to-sequence models are the state-of-the-art approach used in abstractive summarization of textual documents, useful for producing condensed versions of source text narratives without being restricted to using only words from the original text. Despite the advances in abstractive summarization, custom generation of summaries (e.g., towards a user’s preference) remains unexplored. In this article, we present CATS, an abstractive neural summarization model that summarizes content in a sequence-to-sequence fashion while also introducing a new mechanism to control the underlying latent topic distribution of the produced summaries. We empirically illustrate the efficacy of our model in producing customized summaries and present findings that facilitate the design of such systems. We use the well-known CNN/DailyMail dataset to evaluate our model. Furthermore, we present a transfer-learning method and demonstrate the effectiveness of our approach in a low resource setting, i.e., abstractive summarization of meetings minutes, where combining the main available meetings’ transcripts datasets, AMI and International Computer Science Institute(ICSI), results in merely a few hundred training documents. [ABSTRACT FROM AUTHOR]

With the advent of transformer-based architectures, the contextual representation of text data has leveraged the query and the document to be represented in low-dimensional dense vector space. These vectors are learned embeddings of fixed sizes, resulting in deeper text understanding. In this study, we designed a pipeline for effectively retrieving documents from a large search space by combining the deeper text understanding capabilities of the transformer-based BERT model and a phrase embedding-based query expansion model. To learn the contextual representations, we fine-tuned a deep semantic matching model by separately encoding the document and the query. The encoder model is based on the Sentence BERT (SBERT) architecture, which separately generates dense vector representations of documents and queries. The study has also addressed the maximum token length limitation of transformer-based models through the summarization of lengthy documents. In addition, to improve the clarity and completeness of short queries and reduce the semantic gap, a phrase embedding-based query expansion model is employed. The documents and their dense vectors are indexed using the Elasticsearch engine, and matched them with query vectors for retrieving query-specific documents. Finally, the BERT-based cross-encoder model is used to re-rank the relevant records for each query. It performs full self-attention over the inputs, and yields richer text interactions to produce the final results. To assess performance, experiments are conducted on two well-known datasets, TREC-CDS-2014 and OHSUMED. A comparative analysis is carried out, which clearly demonstrates that the proposed framework produced competitive retrieval results. • Transformer-based contextual text representation approach is proposed for IR. • Bi-Encoder architecture is applied to learn the representations of documents & query. • BERT-based summarization is applied to address the limitation on sequence length. • Phrase Embedding-based QE technique is employed to expand short and unclear queries. • Re-ranking of the retrieval results is performed using the cross encoder model. [ABSTRACT FROM AUTHOR]

The Transformer-based summarization models rely solely on the attention mechanism for document encoding, making it difficult to accurately capture long-range dependencies in long documents due to the presence of attention redundancy. To address this issue, we propose an extractive summarization framework guided by a topic model (TopicSum) that utilizes a heterogeneous graph neural network to leverage the topic information as document-level features during the sentence selection process, thereby capturing the long-range dependencies among sentences. The sentence-level features in this topic model align with the basic unit of the extractive summarization task. Additionally, a memory mechanism is employed to dynamically store and update the memory module, reducing the potential of repetitive information guiding sentence selection. We evaluated the model on three large document datasets, namely Pubmed, arXiv, and GovReport, and achieved significantly higher Rouge scores than previous works, including extractive and abstractive models. Furthermore, our experiments demonstrate that recent highly regarded large language models such as ChatGPT are insufficient to handle the long document summarization task directly. The proposed approach in this paper exhibits sufficient competitiveness in terms of both generation quality and deployment conditions. [ABSTRACT FROM AUTHOR]

Abstractive dialogue summarization requires distilling and rephrasing key information from noisy multi-speaker documents. Combining pre-trained language models with input augmentation techniques has recently led to significant research progress. However, existing solutions still struggle to select relevant chat segments, primarily relying on open-domain and unsupervised annotators not tailored to the actual needs of the summarization task. In this paper, we propose DearWatson , a task-aware utterance-level annotation framework for improving the effectiveness and interpretability of pre-trained dialogue summarization models. Precisely, we learn relevant utterances in the source document and mark them with special tags, that then act as supporting evidence for the generated summary. Quantitative experiments are conducted on two datasets made up of real-life messenger conversations. The results show that DearWatson allows model attention to focus on salient tokens, achieving new state-of-the-art results in three evaluation metrics, including semantic and factuality measures. Human evaluation proves the superiority of our solution in semantic consistency and recall. Finally, extensive ablation studies confirm each module's importance, also exploring different annotation strategies and parameter-efficient fine-tuning of large generative language models. [ABSTRACT FROM AUTHOR]

Automatic text summarization is to obtain a summary by compressing the text while retaining its important information. Then users can obtain the important content of the text by reading the summary. In the research literatures, the extraction summary method is widely used and is also one type of the main research methods of summary methods. However, this extraction summary method still has some problems. The selection of the initial cluster center has not been carefully determined, and the sentence redundancy summarized is high in articles with complex sentences. In order to solve the above problems, this paper proposes an automatic text summarization method based on improved TextRank algorithm and K-Means clustering. This method combines the improved BM25 model and the TextRank algorithm to calculate the BM25 similarity between sentences and obtain the TR scores of sentences. The TR scores are used to select the initial center of clustering based on similarity difference judgment and maximum judgment. The final summary is obtained by combining the cluster scores and sentence scores. The experimental results show that the proposed method in this paper has better evaluation indicators containing ROUGE-1, ROUGE-2 and ROUGE-L than other comparison algorithms including Lead-3, TextRank and MBM25EMB on the DUC2004 dataset. In conclusion, the proposed method in this paper improves the accuracy of automatic text summarization and reduce the redundancy from documents. [ABSTRACT FROM AUTHOR]

Development of effective automatic summarization approaches for legal documents suffer from several challenges like extremely long document-summary pairs, lack of large scale training datasets with tractable document-summary token lengths, etc. In this work, we deal with the problem of legal document summarization by building a modified abstractive dataset from the original dataset. This ensures that the length of each document-summary pair is manageable and can be processed by the state of the art summarization approaches (such as BART). Secondly, we deal with the data scarcity problem by creating more number of training samples, from each of the original document-summary pair. This is done by creating multiple extractive summaries from each sample in the original dataset, following which ground-truth summary sentences are assigned to each of the extractive summary to generate new training samples. This results in a larger training dataset that can be utilized for fine-tuning summarization models. Our proposed approach has been evaluated on two different legal datasets- BillSum and Forum of Information Retrieval Evaluation (FIRE). With respect to the ROUGE metrics, the proposed approach is able to outperform pre-trained BART model fine-tuned on original dataset by (3 − 8) % for FIRE test sets, and by (1 − 3) % for the BillSum test sets. Considering the BERTScore metrics, the proposed approach obtains (1 − 2) % improvements on the FIRE test sets, while for the BillSum test sets (3 − 8) % improvements are observed. Such improvements suggest that the proposed dataset building approach can help achieve improved abstractive summarization of lengthy legal documents. • Lengthy nature and data scarcity are the two main challenges with legal documents. • Lengthy legal document summarization is handled by the proposed approach. • The data scarcity problem is handled by creating a feasible abstractive dataset. • A novel Extract-Then-Assign (ETA) approach is proposed. • ETA approach can greatly improve abstractive summarization of legal documents. [ABSTRACT FROM AUTHOR]

Automatically generating a survey draft is a challenge to text summarization research because it needs to select important sentences from important references in a large set of candidate papers for composing sections that are in line with section titles and different sections discuss the most relevant reference papers of different number, which are beyond the capability of previous text summarization approaches as they assume that all candidate papers should be included into one summary. This paper proposes an approach to generating survey draft according to a pattern consisting of sections with titles given by the user who requests the survey. The problem of generating each section can be divided into the following sub-problems: (1) rank the input scientific documents (in short documents) according to the title of a section, (2) determine the number of documents that are most relevant to the title, and (3) rank and select sentences from the selected documents according to the title. A position closeness distance of key word is proposed to rank a set of documents by measuring how closely two key words within section title are distributed within each document, which is used to rank the documents. The rationale is that the positions of the neighboring key words of a section title should be closer in more relevant documents than other words. As different sections have different number of selected documents, a method is proposed to determine the number of documents to be included into the current section based on the slope shape of the sorted rank curve of documents according to the section title. Based on the duality property of the closeness, ranks of sentences within a document can be directly obtained when the document is ranked according to the title of section, and both the importance and coherence of selected sentences can be reflected without extra calculation for ranking sentences. Experiments and manual evaluation show that the proposed methods achieve significant improvements compared with other approaches. The proposed approach is significant in applications as different surveys can be generated according to different patterns given by different users. [ABSTRACT FROM AUTHOR]

In Natural Language Processing (NLP) domain, the majority of automatic text summarization approaches depend on a prior knowledge of the language and/or the domain of the text being summarized. Such approaches requires language dependent part-of-speech taggers, parsers, databases, pre-structured lexicons, etc. In this research, we propose a novel automatic text summarization model, Text Documents - Language Agnostic Summarization Model (TxLASM), which is able to perform extractive text summarization task in language/domain agnostic manner. TxLASM depends on specific characteristics of the major elements of the text being summarized rather than its domain, context, or language and thus rules out the need for language dependent pre-processing tools, taggers, parsers, lexicons or databases. Within TxLASM , we present a novel technique for encoding the shapes of major text elements (paragraphs, sentences, n-grams and words); moreover, we present language independent preprocessing algorithms to normalize words and perform relative stemming or lemmatization. Those algorithms and its Shape-Coding technique enable the TxLASM to extract intrinsic features of text elements and score them statistically, and subsequently extract a representative summary that is independent of the text language, domain and context. TxLASM was applied on an English and Portuguese benchmark datasets, and the results were compared to twelve state-of-the-art approaches presented in recent literature. In addition, the model was applied on French and Spanish news datasets, and the results were compared to those obtained by standard commercial summarization tools. TxLASM has outperformed all the SOTA approaches as well as the commercial tools in all four languages while maintaining its language and domain agnostic nature. [ABSTRACT FROM AUTHOR]

With the development of pre-trained language models and large-scale datasets, automatic text summarization has attracted much attention from the community of natural language processing, but the progress of automatic summarization evaluation has stagnated. Although there have been efforts to improve automatic summarization evaluation, ROUGE has remained one of the most popular metrics for nearly 20 years due to its competitive evaluation performance. However, ROUGE is not perfect, there are studies have shown that it is suffering from inaccurate evaluation of abstractive summarization and limited diversity of generated summaries, both caused by lexical bias. To avoid the bias of lexical similarity, more and more meaningful embedding-based metrics have been proposed to evaluate summaries by measuring semantic similarity. Due to the challenge of accurately measuring semantic similarity, none of them can fully replace ROUGE as the default automatic evaluation toolkit for text summarization. To address the aforementioned problems, we propose a compromise evaluation framework (ROUGE-SEM) for improving ROUGE with semantic information, which compensates for the lack of semantic awareness through a semantic similarity module. According to the differences in semantic similarity and lexical similarity, summaries are classified into four categories for the first time, including good-summary, pearl-summary, glass-summary, and bad-summary. In particular, the back-translation technique is adopted to rewrite pearl-summary and glass-summary that are inaccurately evaluated by ROUGE to alleviate lexical bias. Through this pipeline framework, summaries are first classified by candidate summary classifier, then rewritten by categorized summary rewriter, and finally scored by rewritten summary scorer, which are efficiently evaluated in a manner consistent with human behavior. When measured using Pearson, Spearman, and Kendall rank coefficients, our proposal achieves comparable or higher correlations with human judgments than several state-of-the-art automatic summarization evaluation metrics in dimensions of coherence, consistency, fluency, and relevance. This also suggests that improving ROUGE with semantics is a promising direction for automatic summarization evaluation. [ABSTRACT FROM AUTHOR]

In this paper, we focus on analyzing the relationship between the input of source text and source image, and then through the integration and generalization of the multi-modal information (e.g., texts and images), outputs the multi-modal summarization including text and image. However, existing multi-modal summarization methods face several challenges: (1) Different modalities exist in different semantic spaces, and expressing the multi-modal information of source modalities in a similar semantic representation space is crucial. (2) For the result of text summarization, it is crucial to explore how to capture both the differences and similarities within the source modalities, which can reduce redundancy to improve the quality of text summarization. In order to overcome the challenge above, Multi-Modal Anchor Adaptation Learning for Multi-Modal Summarization (MA-Sum) has been proposed. Specifically, MA-Sum employs a novel and highly efficient image anchor selection method, which selects the object sample containing the richest image information as the image anchor. Simultaneously, it carefully selects the text sentence closely intertwined with the image semantics to serve as the language anchor. Therefore, the multi-modal anchor can be seen as a bridge for multi-modal alignment to alleviate the semantic gap between textual and visual. Moreover, based on the distance between the anchors and the semantic information in the respective modal, the positive and negative semantic information of each modal will be distinguished. Based on negative semantic information, the counterfactual learning mechanism is constructed to optimize the result of multi-modal summarization. Finally, the process of multi-modal features interaction is optimized by image summary which is chosen by using multi-modal anchors. According to the experimental results, compared with the state-of-art multi-modal summarization, our proposed MA-Sum can be optimized in terms of summarization consistency and completeness, so as to obtain the optimal multi-modal summarization metric. [ABSTRACT FROM AUTHOR]

• The select-then-extract framework can better alleviate class imbalance. • Jointing the Extractive Summarization task contributes to the ECPE task. • Multi-granularity cooperative graph can better capture inter-clause relations. • The global keyword helps highlight causal cues implied in distant clauses. • Integrated inference predictor improves the efficiency of reasoning. The class imbalance problem arises in the current end-to-end models for the emotion-cause pair extraction (ECPE) task, and a large number of negative clause pairs interfere model to depict the characteristics of emotion and cause. Most existing methods adopt a window-constrained strategy to limit the relative distance between candidate clauses to a smaller range to filter negative pairs. However, those methods ignore the semantic association between distant clauses, and using an artificial window size is imperfect due to the inherent ambiguity and delicacy of emotion. Inspired by the centrality principle of discourse, in this paper we propose a select-then-extract framework for the ECPE task, where the core clauses are first selected from the original document as candidate emotion and cause clauses, and then emotions, causes and emotion-cause pairs are jointly extracted from the candidate clauses. Specifically, our model includes two main components: core clause selector and emotion-cause pairs extractor. For the Core Clause Selector , we introduce the extractive document summarization (EDS) task and present a multi-granularity semantic awareness cooperative graph model (MGCOG) to extract core clauses from documents. Compared to the previous methods, the core clause selector is more effective for alleviating the category imbalance because the global causal cues and context can be captured by learning global keywords and inter-clause relationships, which determines more efficient candidate clauses. For Emotion-Cause Pairs Extractor , we put forward a multi-task learning model to jointly extract emotions, causes and emotion-cause pairs from the selected core clauses. Here, a multi-head attention is used to further model the relationship between candidate clauses, and a co-predictor is designed for assigning scores to all possible emotion-cause pairs. We further investigate the pipeline and the joint model under the select-then-extract framework, and show that the experimental results on benchmark datasets are consistently superior to the comparative baseline models. Extensive ablation experiments also verify the effectiveness of each component. [ABSTRACT FROM AUTHOR]

Although pretrained language models achieve high performance on various natural language processing tasks, they still require further improvements in the sentence embedding task. Many studies have improved performance in this task using pre-trained language models and contrastive learning, but these approaches are limited because they are based on naive average pooling and CLS tokens. Therefore, we propose an advanced sentence-embedding method based on weighted pooling that considers token importance. Specifically, the token importance is calculated by combining an explainable artificial-intelligence module with a text summarization model, and the final sentence embedding is derived through weighted pooling token embedding and token importance. Thus, we derive a sentence embedding that considers both the local information of the token embedding and the global information of the entire sentence. Experimental results reveal that our proposed sentence embedding outperforms other models on both text similarity tasks and text classification. Moreover, the proposed method's robustness is verified through the results of an ablation study. [ABSTRACT FROM AUTHOR]

• Mapping large-scale, and high spatial resolution ecological quality (EQ) by GEE. • Overall change of EQ in Central Asia is slight inverted U-shaped. • Driving paths for EQ: urbanization, agriculture, resource, climate and policy. • Land use intensity and agricultural water use efficiency are main factors for EQ. • Interaction between human and natural factors are increasingly important for EQ. With the frequent occurrence of worldwide extreme climate events, human-induced ecosystem degradation has seriously threatened the realization of the Sustainable Development Goals (SDGs), especially in arid ecologically fragile areas. Macro-scale ecological quality (EQ) monitoring and exploration of its driving mechanisms have become research hotspots. However, this research field still lacks a method framework with strong comparability, adaptability and transferability, which significantly restricts the applicability of research results. In this study, a method framework for exploring spatial and temporal changes in EQ and their driving mechanisms based on text summarization and information extraction is constructed. Taking Central Asia as a typical case, this study outlines its EQ driving paths, explores the influencing mechanisms of representative drivers, and verifies the effectiveness of this method framework based on the comparison of the spatial and temporal evolution of EQ at multiple scales. The results indicate that the overall EQ in Central Asia exhibited a slight inverted U-shaped trend, with its driving paths falling into five categories: urban expansion, agricultural development, resource extraction, climate change, and ecological protection. The fragmentation of areas with high EQ is the main landscape characteristic in Central Asia. Furthermore, land use intensity and agricultural water use efficiency are significant factors in Central Asia's EQ evolution. Over time, the interaction between anthropogenic and natural factors has played an essential role in EQ evolution in Central Asia, with interactions between altitude, climate aridity, agricultural water use efficiency, and land use intensity gradually intensifying. This study has an implication for the construction of method framework for EQ-related study in ecologically fragile areas at the macro scale. [ABSTRACT FROM AUTHOR]

The rapid development of textual data requires an automated text summarization system to obtain shortened versions of documents quickly and accurately. This paper investigates the performances of BertSum and Pointer Generator Network (PGN) on the IndoSum corpus containing Indonesian news articles. We compare these methods to NeuralSum, which is claimed to outperform other methods when working with the IndoSum dataset. In our experiment, BertSum with Indonesian's pre-trained model outperformed NeuralSum in extractive summarization. NeuralSum, on the other hand, tends to select the leading sentences as a summary and occasionally produces a blank summary. Meanwhile, PGN effectively prevents word repetition by using a coverage mechanism, although the summary results are sometimes out of context. [ABSTRACT FROM AUTHOR]

It is essential to provide a structured data feed to the computer to accomplish any task so that it can process flawlessly to generate the desired output within minimal computational time. Generally, computer programmers should provide a structured data feed to the computer program for its successful execution. The hardcopy document should be scanned to generate its corresponding computer-readable softcopy version of the file. This process also proves to be a budget-friendly approach to disengage human resources from the entire process of record maintenance. Due to this automation, the workload of existing manpower is reduced to a significant level. This concept may prove beneficial for the delivery of any type of services to the ultimate beneficiary (i.e., citizen) in a minimal time frame. The administration has to deal with various issues of citizens due to the pressure of a huge population who seek legal help to resolve their issues, thereby leading to the filing of large numbers of pending legal cases at several courts of the country. To assist the victims with prompt delivery of justice and legal professionals in reducing their workload, this paper proposed a machine learning based automated legal model to enhance the efficiency of the legal support system with an accuracy of 94%. [ABSTRACT FROM AUTHOR]

According to the problem that the model in the generative text summarization doesn’t fully understand the semantics of the text and the generated summary lacks key information, this paper proposed a Key-BERT-Pen model that integrated keywords in Chinese abstract generation. The KBPM first used the TextRank method to extract the keywords in the text, and then obtained a more accurate contextual representation through the BERT pre-training model using the extracted keywords and the original text. Finally, it input the obtained word vector into a pointer model with a dual attention mechanism, and the pointer model took vocabularies from the vocabulary or original text to generate the final abstract. Experimental results show that the KBPM can generate text summaries with better readability and higher ROUGE scores. The comparative analysis also verifies that the KBPM effectively solves the problem of the lack of key information in the generated abstract. [ABSTRACT FROM AUTHOR]

Having control over your data is a right and a duty that every citizen has in our digital society. It is often that users skip entire policies of applications or websites to save time and energy without realizing the potential sticky points in these policies. Due to obscure language and verbose explanations majority of users of hypermedia do not bother to read them. Further, sometimes digital media companies do not spend enough effort in stating their policies clearly which often time can also be incomplete. A summarized version of these privacy policies that can be categorized into the useful information can help the users. To solve this problem, in this work we propose to use machine learning-based models for policy categorizer that classifies the policy paragraphs under the attributes proposed like security, contact, etc. By benchmarking different machine learning-based classifier models, we show that artificial neural network model performs with higher accuracy on a challenging dataset of textual privacy policies. We thus show that machine learning can help summarize the relevant paragraphs under the various attributes so that the user can get the gist of that topic within a few lines. [ABSTRACT FROM AUTHOR]

Precision education is a new challenge in leveraging artificial intelligence, machine learning, and learning analytics to enhance teaching quality and learning performance. To facilitate precision education, text marking skills can be used to determine students' learning process. Text marking is an essential learning skill in reading. In this study, we proposed a model that leverages the state-of-the-art text summarization technique, Bidirectional Encoder Representations from Transformers (BERT), to calculate the marking score for 130 graduate students enrolled in an accounting course. Then, we applied learning analytics to analyze the correlation between their marking scores and learning performance. We measured students' self-regulated learning (SRL) and clustered them into four groups based on their marking scores and marking frequencies to examine whether differences in reading skills and text marking influence students' learning performance and awareness of self-regulation. Consistent with past research, our results did not indicate a strong relationship between marking scores and learning performance. However, high-skill readers who use more marking strategies perform better in learning performance, task strategies, and time management than high-skill readers who use fewer marking strategies. Furthermore, high-skill readers who actively employ marking strategies also achieve superior scores of environment structure, and task strategies in SRL than low-skill readers who are inactive in marking. The findings of this research provide evidence supporting the importance of monitoring and training students' text marking skill and facilitating precision education. [ABSTRACT FROM AUTHOR]

Aiming at the traditional graph models for text summarization only focus on statistical features or shallow semantic features, and lack mining and utilization of deep topic semantic features, this paper proposed MDSR( multi-dimension summarization rank), an automatic text summarization method that combined topic feature. Specifically, this method adopted the LDA model to mine the semantic information of text topics and measured the impact of topic feature on a sentence by defining the importance of the topic. And it improved the construction mode of the probability transition matrix of graph model nodes by combining the topic feature with statistic features and inter-sentence similarity. Finally, it extracted and measured summarization according to the weight of sentence nodes. The results show that the ROUGE value evaluates by MDSR reaches the best when the weight ratio of topic feature, statistic feature and inter-sentence similarity is 3 : 4 : 3. The ROUGE-1, ROUGE-2, ROUGE-SU4 are 53. 35%,35. 18% and 33. 86%, which perform better than other comparisons. It shows that the text summarization method combining topic feature can effectively improve the accuracy of the summarization extraction. [ABSTRACT FROM AUTHOR]

Recently, large language models have shown great success on various abstractive summarization datasets. These datasets consist of numerous data that are enough to train a large number of parameters. However, for a new domain, there is a lack of labeled data to train those parameters and the model is easily overfitted to a small amount of data. In addition, because annotating document-summary pairs is too expensive and transfer learning using high-resource datasets causes a domain shifting problem, a low-resource abstractive summarization task is becoming necessary. Herein, we propose an efficient framework for low-resource abstractive summarization using a pointer-generator network and a meta-learning technique to address the above problems. Meta-learning using existing high-resource datasets enables our model to rapidly adapt to a new domain using limited data to solve the domain shifting problem. In addition, we explore the copy mechanism using a pointer-generator network that can copy words from a source document when generating a summary. The experimental results on 11 different datasets show that the proposed model outperforms the previous state-of-the-art models in low-resource abstractive summarization on most of the datasets. [ABSTRACT FROM AUTHOR]

A long-running event represents a continuous stream of information on a given topic, such as natural disasters, stock market updates, or even ongoing customer relationship. These news stories include hundreds of individual, time-dependent texts. Simultaneously, new technologies have profoundly transformed the way we consume information. The need to obtain quick, relevant, and digest updates continuously has become a crucial issue and creates new challenges for the task of automatic document summarization. To that end, we introduce an innovative unsupervised method based on two competing sequence-to-sequence models to produce short updated summaries. The proposed architecture relies on several parameters to balance the outputs from the two autoencoders. This relation enables the overall model to correlate generated summaries with relevant information coming from both current and previous news iterations. Depending on the model configuration, we are then able to control the novelty or the consistency of terms included in generated summaries. We evaluate our method on a modified version of the TREC 2013, 2014, and 2015 datasets to track continuous events from a single source. We not only achieve state-of-the-art performance similar to other more complex unsupervised sentence compression approaches, but also influence the information included in the model in the summaries. • Incremental summarization of real-time news events. • Unsupervised autoencoder for summarization of short texts related to the same event. • Semi-extractive method of accounting for information updates in the sentence compression task. • Promoting novelty or cohesion of information in incremental and update summarization processes. [ABSTRACT FROM AUTHOR]

The primary challenge faced in extractive text summarization is related to the scoring of sentences, with the critical factor for scoring being the manner in which the sentence representation is conducted. This study aims to investigate this hypothesis and to perform a detailed analysis of the impact of sentence representation techniques that have been used both semantically and syntactically. The study initially evaluated the empirical impact of individual syntactic and semantic features on the accuracy of summarization. To examine syntactic usage, a comprehensive list of 40 syntactic features was developed, while semantic representation was accomplished using sentence embeddings. Subsequently, an improved feature set was proposed that jointly utilizes syntactic and semantic features. To assess the impact of this feature set on the resulting summaries, the proposed sentence representation was tested on three distinct summarization corpora consisting of lengthy scientific documents across diverse domains. The assessment of summary evaluation and classification performance evaluation metrics was conducted to evaluate the quality of the resulting summaries. The findings of the experiments indicated that the summaries generated by the proposed feature set performed better than not only those obtained using individual features but even summaries produced by state-of-the-art methods. • In literature, text summarization has been handled by syntactic or semantic approach. • A new enhanced sentence representation was proposed to score sentences. • The sentence scoring model was a random forest fed by this enhanced representation. • The proposed model remarkably outperformed the baseline and state-of-the-art models. [ABSTRACT FROM AUTHOR]

Traditional seq2seq model didn' t fully utilize the sentence structure of the input text, this results in that seq2seq model can't generate a text summary with rigorous structure and better grammar. Therefore, the paper proposed a summary generation method with basic structure of sentence. First of all, it explicitly proposed the concept of generating a text summary with sentence structure. Furthermore, it added a sentence structure module and a supervisor module on the summary generator. The sentence structure module captured a series of sentence structures from the input text, the supervisor module evaluated the importance of the sentence structures, this assisted the sentence structure module to capture some available sentence structures. Finally, the summary generator combined the available sentence structures to generate the final summary. The experiments on LCSTS show that its ROUGE scores are higher than seq2seq. In other words,its accuracy surpasses seq2seq. Experiments also verify the necessity of the existence of the sentence structure module and the supervisor module. [ABSTRACT FROM AUTHOR]

Natural language processing is the trending topic in the latest research areas, which allows the developers to create the human-computer interactions to come into existence. The natural language processing is an integration of artificial intelligence, computer science and computer linguistics. The research towards natural Language Processing is focused on creating innovations towards creating the devices or machines which operates basing on the single command of a human. It allows various Bot creations to innovate the instructions from the mobile devices to control the physical devices by allowing the speech-tagging. In our paper, we design a search engine which not only displays the data according to user query but also performs the detailed display of the content or topic user is interested for using the summarization concept. We find the designed search engine is having optimal response time for the user queries by analyzing with number of transactions as inputs. Also, the result findings in the performance analysis show that the text summarization method has been an efficient way for improving the response time in the search engine optimizations. [ABSTRACT FROM AUTHOR]

Currently, the prominence of automatic multi document summarization task belongs to the information rapid increasing on the Internet. Automatic document summarization technology is progressing and may offer a solution to the problem of information overload. Automatic text summarization system has the challenge of producing a high quality summary. In this study, the design of generic text summarization model based on sentence extraction has been redirected into a more semantic measure reflecting individually the two significant objectives: content coverage and diversity when generating summaries from multiple documents as an explicit optimization model. The proposed two models have been then coupled and defined as a single-objective optimization problem. Also, for improving the performance of the proposed model, different integrations concerning two similarity measures have been introduced and applied to the proposed model along with the single similarity measures that are based on using Cosine, Dice and Jaccard similarity measures for measuring text similarity. For solving the proposed model. Genetic Algorithm (GA) has been used. Document sets supplied by Document Understanding Conference 2002 (DUC2002) have been used for the proposed system as an evaluation dataset. Also, as an evaluation metric, Recall-Oriented Understudy for Gisting Evaluation (ROUGE) toolkit has been used for performance evaluation of the proposed method. Experimental results have illustrated the positive impact of measuring text similarity using double integration of similarity measures against single similarity measure when applied to the proposed model wherein the best performance in terms of Rouge - 2 (0.1354) and Rouge - 1 (0.4210) has been recorded for the integration of Cosine similarity and Jaccard similarity. [ABSTRACT FROM AUTHOR]

Currently, each person produces 1.7MB of information every second in different formats. However, the vast majority of information is text. This has increased the interest to study techniques to automate the identification of the relevant portions of text documents in order to offer as a result an automatic summary. This article presents a technique to extract the most representative sentences of a document taking into account by the user's criteria. These criteria are learned using a neural network, from a minimum set of documents whose sentences have been rated by the user in terms of importance. To verify the performance of the proposed methodology, we used 220 scientific articles from the PLOS Medicine journal published between 2004 and 2016. The results obtained have been very satisfactory. [ABSTRACT FROM AUTHOR]

In this paper, we focus on designing and implementing SmartMeeting, an intelligent system for generating meeting minutes from meeting audio data. SmartMeeting mainly consists of four parts: the first part is the meeting speech detection, which is used to automatically extract multiple speech segments of each speaker and then sort them by time, and mark the corresponding speakers separately in different time periods; The second part is the meeting voice text transcription, the voice segment cut in the previous step is transcribed into a complete meeting text; The third part is the extraction of the meeting minutes, extracting meaningful key phrases and abstract sentences from the complete meeting text; The fourth part is the next work plan extraction, through the emotion recognition algorithm to filter out the negative emotion summary from the multiple meeting minutes, so as to show the next work plan of the meeting. By comparing and evaluating different baseline algorithms on real-world audio meeting datasets, experiments have proven that SmartMeeting can accurately summarize meetings and analyze agreed actions. [ABSTRACT FROM AUTHOR]

Automatic text summarization is a field situated at the intersection of natural language processing and information retrieval. Its main objective is to automatically produce a condensed representative form of documents. This paper presents ArA*summarizer, an automatic system for Arabic single document summarization. The system is based on an unsupervised hybrid approach that combines statistical, cluster‐based, and graph‐based techniques. The main idea is to divide text into subtopics then select the most relevant sentences in the most relevant subtopics. The selection process is done by an A* algorithm executed on a graph representing the different lexical–semantic relationships between sentences. Experimentation is conducted on Essex Arabic summaries corpus and using recall‐oriented understudy for gisting evaluation, automatic summarization engineering, merged model graphs, and n‐gram graph powered evaluation via regression evaluation metrics. The evaluation results showed the good performance of our system compared with existing works. [ABSTRACT FROM AUTHOR]

The method of Chinese existing automatic text summarization mainly utilizes the text's own information, and its defect is that it cannot make full use of the related semantic information between the words. Therefore, this paper proposed an improved Chinese text summarization method. This method integrated the information of the external corpora into the TextRank algorithm in the form of a word vector. Combined TextRank with word2vec, it mapped each word in the sentence to the high dimensional lexicon to form a sentence vector. This method fully considered the similarity between sentences, the coverage of keywords and the similarity between sentence and title to calculate the influence weights among sentences, and choose the top-ranked sentences used as the summarization of the text. The results of experiment show that this method achieves good results in the data set of this paper, and is more effective than the original method in extracting Chinese summarization automatically. [ABSTRACT FROM AUTHOR]

Extractive text summarization yields the sensitive parts of the document by neglecting the irrelevant and redundant information. In this paper, we propose a new strategy for extractive single-document summarization in Malayalam. Initially, entity recognition is done, followed by relevance analysis is made based on some context-aware features. The scored sentences are then clustered using self-organizing maps (SOM) and from these clusters, relevant sentences are extracted out based on the proposed algorithm. Both theoretical and practical evaluations are done to analyze the implemented system. In theoretical evaluation, gradient calculations of relevance equations are used to know that which of these sentence scoring features are contributing more. The relevance equation is optimized with the help of Lagrange's multiplier. The complexity analysis of the proposed algorithms is also performed. In practical evaluation, the system compared with online and offline summarizers upon metrics like precision, recall, and F-measure. The system is tested through a non-clustering approach also in order to analyze the impact of clustering used in our work. Some existing strategies like question game evaluation, sentence rank evaluation, and keyword association are also done to evaluate the different parameters like the relevance of sentences, important entity words, etc. [ABSTRACT FROM AUTHOR]

With the commencement of new technology, demands of online shopping are increasing day by day and hence an electronic product receives a huge number of customers reviews everyday. Because of this, a customer who wants to buy a particular product face difficulty as he needs to go through all the reviews of that product before taking a final decision. Automatically generated summary of the reviews could aid the customers in selecting the appropriate product. Aiming in this direction, a novel approach for making automatic extractive text summaries of the reviews for various electronic products is proposed in this paper. We have taken into account both the content of the review and the author's credibility while evaluating the importance of a sentence. Both the content and semantic similarities are measured between every pair of sentences of a review. In order to form the summary of the reviews, fuzzy c-means clustering is used. For experimental purpose, Amazon dataset is used and the results indicate that the proposed method outperforms some of the baseline methods for generating the summary of the reviews, thus providing more concrete and robust summary. [ABSTRACT FROM AUTHOR]

Currently, automatic multi-document text summarization is an important task in many fields of knowledge, due to the continuous exponential growth of information on the Internet. Nevertheless, this task is computationally demanding. In the last years, automatic text summarization has been addressed by using multi-objective optimization approaches. In particular, recently, the Multi-Objective Artificial Bee Colony (MOABC) algorithm has obtained very good results. This work focuses on the parallelization of this approach. Several steps have been carried out for this goal. After a time profiling of the algorithm, a runtime comparison has been performed between the use of different random number generators within the algorithm. Then, a parallel implementation of the MOABC algorithm has been designed following its original scheme, in which the main steps are parallelized, and different parallel schedules have been studied and compared. Finally, a second design based on the asynchronous behavior of the bee colony in nature has been implemented and compared. Experiments have been carried out with datasets from Document Understanding Conference (DUC). The results show that the asynchronous design improves greatly the parallel design, being more than 55 times faster with 64 threads than the standard design. An efficiency of 86.72% has been reported for 64 threads. • Nowadays, automatic extractive multi-document summarization is an important task. • However, automatic multi-document text summarization is computationally costly. • A complete parallelism study is presented here, evaluating different alternatives. • The asynchronous parallel design has obtained the best performance results. • In fact, this parallel design reports an efficiency of 86.72% for 64 threads. [ABSTRACT FROM AUTHOR]

• Statistical feature based extractive approach for multi-document summarization. • Fuzzy logic system is used for sentence scoring. • Cosine similarity measure is used to tackle redundancy from summary. Nowadays abundant amount of information is available on Internet which makes it difficult for the users to locate desired information. Automatic methods are needed to efficiently sieve and scavenge useful information from the Internet. Text summarization is identified and accepted as one of the solutions to find desired contents from one or more documents. The objective of proposed multi-document summarization is to gain good content coverage with information diversity. The proposed statistical feature based model utilizes the fuzzy model to deal with the imprecise and uncertainty of feature weight. Redundancy removal using cosine similarity is presented as enrichment to proposed work. The proposed approach is compared with DUC (Document Understanding Conference) participant systems and other summarization systems such as TexLexAn, ItemSum, Yago Summarizer, MSSF and PatSum using ROUGE measure on dataset DUC 2004. The experimental results show that our proposed work achieves a significant performance improvement over the other summarizers. [ABSTRACT FROM AUTHOR]

Purpose: Whether automatically generated summaries of health social media can aid users in managing their diseases appropriately is an important question. The purpose of this paper is to introduce a novel text summarization approach for acquiring the most informative summaries from online patient posts accurately and effectively. Design/methodology/approach: The data set regarding diabetes and HIV posts was, respectively, collected from two online disease forums. The proposed summarizer is based on the graph-based method to generate summaries by considering social network features, text sentiment and sentence features. Representative health-related summaries were identified and summarization performance as well as user judgments were analyzed. Findings: The findings show that awarding sentences without using all the incorporating features decreases summarization performance compared with the classic summarization method and comparison approaches. The proposed summarizer significantly outperformed the comparison baseline. Originality/value: This study contributes to the literature on health knowledge management by analyzing patients' experiences and opinions through the health summarization model. The research additionally develops a new mindset to design abstractive summarization weighting schemes from the health user-generated content. [ABSTRACT FROM AUTHOR]

Automatic text summarization is a process of condensing the content of a text document to pursue the most important information. It plays a significant role in various tasks like text categorization, question answering and information retrieval (IR). As legal information retrieval (LIR) is a subfield of IR, the produced summaries are combined into IR system, with the objective of decreasing the length of the document. In this way, we can improve the access time for searching the information, and relevant documents are retrieved. In this article, we present the creation of passage-level summaries (generic and legal) with different compression ratios and evaluate their performance. The generic summaries present the overall description of the essential information of a document and legal summaries, produced by taking into account the domain-specific features that are present in the document. Next, we propose Boosting Okapi BM25 which is the modified model of Okapi BM25 to increase the efficiency of the LIR. We have evaluated proposed LIR approach in terms of MAP and R-precision and summarization approach using ROUGE tool on FIRE2013 and FIRE2014 datasets. To show the efficacy of the proposed system, we compare the experimental results with different IR models like PL2, I n _ e x p B 2 , I n _ e x p C 2 , InL2, D F R _ B M 25 , Okapi BM25 in terms of MAP. The experimental results of the proposed system show better performance than the existing various IR models in terms of various performance metrics. The empirical results also exhibit that the integration of text summarization and IR techniques helps in retrieving relevant information with less access time. [ABSTRACT FROM AUTHOR]

• A hybrid approach to learn and represent users' preference knowledge. • Users' preference knowledge representation supplements ratings prediction. • Extending latent factor model to include acquired preference knowledge. • Experiments on Amazon products datasets shows performance improvements. Some existing preference prediction methods have utilized users' review texts to learn additional knowledge to support the prediction task. Such methods determine and represent users' preference knowledge by conducting user sentiment, aspect sentiment and topic analysis as recognized in the review texts. However, the discovered item topics from topic-based methods may not fit the preferences of most users while the discovered users' opinions and aspects' sentiments from sentiment based methods may not reflect each user's opinion. This paper proposes a hybrid approach to learn and represent users' preference knowledge from review texts and utilize the acquired representation to support rating prediction. Our approach assumes that user preferences are affected by relevant item aspects and majority preference which can be captured through proper summarization and representation of users' review texts. Thus, two deep learning practices are established: the recurrent neural network - Long Short-Term Memory (RNN-LSTM) architecture to learn users' preference knowledge along with item aspects which influence preferences and the Doc2Vec algorithm to convert the acquired knowledge to a suitable representation. The approach extends probabilistic matrix factorization (PMF) model by strengthening its latent factors predictions with the acquired preference knowledge which is used to regulate the predictions. Our experiments on the Amazon products dataset have revealed the capability of learning a suitable representation for users' preference knowledge and its impact on rating prediction as our proposed approach beats alternative methods. [ABSTRACT FROM AUTHOR]

With the rapid development of clinical and laboratory medicine, the field of bioinformatics boasts of extensive clinical records and research literature. Retrieving effective information from this huge data has become a challenging task. Hence, Intelligent text summarization, which enables users to find and understand relevant source texts more quickly and effortlessly, becomes a very significant and valuable field of research. In this study, we propose an improved TextRank algorithm with weight calculation based on sentence graph to solve this problem. For the experimental dataset obtained from Pubmed, we represent terms as vectors by using Skip-gram model. We design three methods which utilize word embeddings to calculate weights between sentences. Then we build an undirected graph with sentences as nodes. At last, we use the improved TextRank algorithm to calculate the importance of sentences and further generated summarizations base on its ranking. The experimental results and analysis on the datasets demonstrate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

• We proposed a novel summary method by using code vector of autoencoder. • Unsupervised abstractive summarization using Adversarially regularized autoencoder. • Conditional model is proposed and enhanced performance for review summarization. Abstractive summarization is challenging problem, especially abstractive summarization based on unsupervised learning because it must generate whole, unique sentences. In the real world, companies use abstractive summarization to understand customer feedbacks. In many cases, this work is done by humans and so is expensive in terms of time and money. Therefore, there is an increasing demand for machine learning-based abstractive summarization systems. However, most previous abstractive summarization studies were of supervised models. In this paper, we proposed novel abstractive summarization methods that can be trained unsupervisedly. One of the proposed methods is based on Adversarially Regularized Autoencoder(ARAE) model, but abstractive summary generation method for each cluster of similar customers' reviews, is newly proposed. We further proposed Conditional Adversarially Regularized Autoencoder(CARAE) model which is similar to the ARAE model but with the addition of condition nodes so that additional information about the cluster can be used during summarization. We first performed summary experiments based on Korean and additionally performed experiments on English. In the experiments, we set up some comparison models and used ROUGE and BLEU to evaluate our proposed models' performance. Overall, our proposed models outperformed the comparison models and CARAE model performed better than the ARAE model. [ABSTRACT FROM AUTHOR]

Fuzzy Rough Sets are designed for decision-making with uncertainty, imprecision, and incompleteness in data. We propose to use Fuzzy Rough Sets for the task of sentence similarity-based Text Summarization. Text data inherently possess uncertainty, imprecision, and incompleteness for data representation. Two sentences may be equivalent in their meanings despite having different vector space representation while Fuzzy Rough Sets incorporates the meanings of sentences. Fuzzy Rough Set-based sentence similarity for Text Summarization has not been proposed in literature before the present work. The contribution of the research is two-fold, namely (i) Fuzzy Rough Set-based sentence similarities has been proposed and validated on SICK2014 dataset. (ii) The proposed similarities between the sentences are thereby proposed for Single document Text Summarization and evaluated for DUC2002 dataset. Experimental results confirm the applicability and efficiency of using the proposed models for both sentence similarity computations as well as for summarization. [ABSTRACT FROM AUTHOR]

Purpose: Text summarization of clinical trial descriptions has the potential to reduce the time required to familiarize oneself with the subject of studies by condensing long-form detailed descriptions to concise, meaning-preserving synopses. This work describes the process and quality of automatically generated summaries of clinical trial descriptions using extractive text summarization methods.Methods: We generated a novel dataset from the detailed descriptions and brief summaries of trials registered on clinicaltrials.gov. We executed several text summarization algorithms on the detailed descriptions in this corpus and calculated the standard ROUGE metrics using the brief summaries included in the record as a reference. To investigate the correlation of these metrics with human sentiments, four reviewers assessed the content-completeness of the generated summaries and the helpfulness of both the generated and reference summaries via a Likert scale questionnaire.Results: The filtering stages of the dataset generation process reduce the 277,228 trials registered on clinicaltrials.gov to 101,016 records usable for the summarization task. On average, the summaries in this corpus are 25% the length of the detailed descriptions. Of the evaluated text summarization methods, the TextRank algorithm exhibits the overall best performance with a ROUGE-1 F1 score of 0.3531, ROUGE-2 F1 score of 0.1723, and ROUGE-L F1 score of 0.3003. These scores correlate with the assessment of the helpfulness and content similarity by the human reviewers. Inter-rater agreement for the helpfulness and content similarity was slight and fair respectively (Fleiss' kappa of 0.12 and 0.22).Conclusions: Extractive summarization is a viable tool for generating meaning-preserving synopses of detailed clinical trial descriptions. Further, the human evaluation has shown that the ROUGE-L F1 score is useful for rating the general quality of generated summaries of clinical trial descriptions in an automated way. [ABSTRACT FROM AUTHOR]

Generative transformer-based models have achieved state-of-the-art performance in text summarization. Nevertheless, they still struggle in real-world scenarios with long documents when trained in low-resource settings of a few dozen labeled training instances, namely in low-resource summarization (LRS). This paper bridges the gap by addressing two key research challenges when summarizing long documents, i.e., long-input processing and document representation, in one coherent model trained for LRS. Specifically, our novel align-then-abstract representation learning model (Athena) jointly trains a segmenter and a summarizer by maximizing the alignment between the chunk-target pairs in output from the text segmentation. Extensive experiments reveal that Athena outperforms the current state-of-the-art approaches in LRS on multiple long document summarization datasets from different domains. [ABSTRACT FROM AUTHOR]

Highlights • Word2vec representation improves the summarization task compared to bag of words. • Feature learning using unsupervised neural networks improves the summarization task. • Unsupervised neural networks trained on word2vec vectors gives promising results. • Ensemble learning with word2vec representation obtains the best results. Abstract The vast amounts of data being collected and analyzed have led to invaluable source of information, which needs to be easily handled by humans. Automatic Text Summarization (ATS) systems enable users to get the gist of information and knowledge in a short time in order to make critical decisions quickly. Deep neural networks have proven their ability to achieve excellent performance in many real-world Natural Language Processing and computer vision applications. However, it still lacks attention in ATS. The key problem of traditional applications is that they involve high dimensional and sparse data, which makes it difficult to capture relevant information. One technique for overcoming these problems is learning features via dimensionality reduction. On the other hand, word embedding is another neural network technique that generates a much more compact word representation than a traditional Bag-of-Words (BOW) approach. In this paper, we are seeking to enhance the quality of ATS by integrating unsupervised deep neural network techniques with word embedding approach. First, we develop a word embedding based text summarization, and we show that Word2Vec representation gives better results than traditional BOW representation. Second, we propose other models by combining word2vec and unsupervised feature learning methods in order to merge information from different sources. We show that unsupervised neural networks models trained on Word2Vec representation give better results than those trained on BOW representation. Third, we also propose three ensemble techniques. The first ensemble combines BOW and word2vec using a majority voting technique. The second ensemble aggregates the information provided by the BOW approach and unsupervised neural networks. The third ensemble aggregates the information provided by Word2Vec and unsupervised neural networks. We show that the ensemble methods improve the quality of ATS, in particular the ensemble based on word2vec approach gives better results. Finally, we perform different experiments to evaluate the performance of the investigated models. We use two kind of datasets that are publically available for evaluating ATS task. Results of statistical studies affirm that word embedding-based models outperform the summarization task compared to those based on BOW approach. In particular, ensemble learning technique with Word2Vec representation surpass all the investigated models. [ABSTRACT FROM AUTHOR]

Inspired by the millions of Electronic Theses and Dissertations (ETDs) openly available online, we describe a novel use of ETDs as data for text summarization. We use a large corpus of ETDs to evaluate techniques for generating abstractive summaries with deep learning. Using an extensive ETD collection of over 30,000 doctoral dissertations and master’s theses, we examine the quality of state-of-the-art deep learning summarization technologies when applied to an ETD corpus. Deep learning requires a large set of training data to produce satisfactory results. Finding suitable training data is especially difficult due to the widespread use of domain-specific jargon in ETDs, coupled with the wide-ranging breadth of subject matter contained in an ETD corpus. To overcome this significant limitation, we demonstrate the potential of transfer learning on automatic summarization of ETD chapters. We apply several combinations of deep learning models and training data to the ETD chapter summarization task and compare the outputs of the top performers. [ABSTRACT FROM AUTHOR]

Abstract Due to the tremendous increment of data on the web, extracting the most important data as a conceptual brief would be valuable for certain users. Therefore, there is a massive enthusiasm concerning the generation of automatic text summary frameworks to constitute abstracts automatically from the text, web, and social network messages associated with their satellite content. This survey highlights, for the first time, how the swarm intelligence (SI) optimization techniques are performed to solve the text summarization task efficiently. Additionally, a convincing justification of why SI, especially Ant Colony Optimization (ACO), has been presented. Unfortunately, three types of text summarization tasks using SI indicate bit utilizing in the literature when contrasted with the other summarization techniques as machine learning and genetic algorithms, in spite of the fact that there are seriously promising outcomes of the SI methods. On the other hand, it has been noticed that the summarization task with multiple types has not been formalized as a multi-objective optimization (MOO) task before, despite that there are many objectives which can be considered. Moreover, the SI was not employed before to support the real-time summary approaches. Thus, a new model has been proposed to be adequate for achieving many objectives and to satisfy the real-time needs. Eventually, this study will enthuse researchers to further consider the various types of SI when solving the summarization tasks, particularly, in the short text summarization (STS) field. [ABSTRACT FROM AUTHOR]

This article proposes the modified KNN (K Nearest Neighbor) algorithm which receives a string vector as its input data and is applied to the text summarization. The results from applying the string vector based algorithms to the text categorizations were successful in previous works and the text summarization is able to be viewed into a binary classification where each paragraph is classified into summary or non-summary. In the proposed system, a text which is given as the input is partitioned into a list of paragraphs, each paragraph is classified by the proposed KNN version, and the paragraphs which are classified into summary are extracted ad the output. The proposed KNN version is empirically validated as the better approach in deciding whether each paragraph is essential or not in news articles and opinions. We need to define and characterize mathematically more operations on string vectors for modifying more advanced machine learning algorithms. [ABSTRACT FROM AUTHOR]

Semantic applications typically exploit structures such as dependency parse trees, phrase-chunking, semantic role labeling or open information extraction. In this paper, we introduce a novel application of Open IE as an intermediate layer for text summarization. Text summarization is an important method for providing relevant information in large digital libraries. Open IE is referred to the process of extracting machine-understandable structural propositions from text. We use these propositions as a building block to shorten the sentence and generate a summary of the text. The proposed system offers a new form of summarization that is able to break the structure of the sentence and extract the most significant sub-sentential elements. Other advantages include the ability to identify and eliminate less important sections of the sentence (such as adverbs, adjectives, appositions or dependent clauses), or duplicate pieces of sentences which in turn opens up the space for entering more sentences in the summary to enhance the coverage and coherency of it. The proposed system is localized for Persian language; however, it can be adopted to other languages. Experiments performed on a standard data set “Pasokh” with a standard comparison tool showed promising results for the proposed approach. We used summaries produced by the system in a real-world application in the virtual library of Shahid Beheshti University and received good feedbacks from users. [ABSTRACT FROM AUTHOR]

The rapid growth of scientific literature has made it difficult for the researchers to quickly learn about the developments in their respective fields. Scientific summarization addresses this challenge by providing summaries of the important contributions of scientific papers. We present a framework for scientific summarization which takes advantage of the citations and the scientific discourse structure. Citation texts often lack the evidence and context to support the content of the cited paper and are even sometimes inaccurate. We first address the problem of inaccuracy of the citation texts by finding the relevant context from the cited paper. We propose three approaches for contextualizing citations which are based on query reformulation, word embeddings, and supervised learning. We then train a model to identify the discourse facets for each citation. We finally propose a method for summarizing scientific papers by leveraging the faceted citations and their corresponding contexts. We evaluate our proposed method on two scientific summarization datasets in the biomedical and computational linguistics domains. Extensive evaluation results show that our methods can improve over the state of the art by large margins. [ABSTRACT FROM AUTHOR]

Feature Maximization is a feature selection method that deals efficiently with textual data: to design systems that are altogether language-agnostic, parameter-free and do not require additional corpora to function. We propose to evaluate its use in text summarization, in particular in cases where documents are structured. We first experiment this approach in a single-document summarization context. We evaluate it on the DUC AQUAINT corpus and show that despite the unstructured nature of the corpus, our system is above the baseline and produces encouraging results. We also observe that the produced summaries seem robust to redundancy. Next, we evaluate our method in the more appropriate context of SciSumm challenge, which is dedicated to research publications summarization. These publications are structured in sections and our class-based approach is thus relevant. We more specifically focus on the task that aims to summarize papers using those that refer to them. We consider and evaluate several systems using our approach dealing with specific bag of words. Furthermore, in these systems, we also evaluate cosine and graph-based distance for sentence weighting and comparison. We show that our Feature Maximization based approach performs very well in the SciSumm 2016 context for the considered task, providing better results than the known results so far, and obtaining high recall. We thus demonstrate the flexibility and the relevance of Feature Maximization in this context. [ABSTRACT FROM AUTHOR]

Abstract Huge volumes of textual information has been produced every single day. In order to organize and understand such large datasets, in recent years, summarization techniques have become popular. These techniques aims at finding relevant, concise and non-redundant content from such a big data. While network methods have been adopted to model texts in some scenarios, a systematic evaluation of multilayer network models in the multi-document summarization task has been limited to a few studies. Here, we evaluate the performance of a multilayer-based method to select the most relevant sentences in the context of an extractive multi document summarization (MDS) task. In the adopted model, nodes represent sentences and edges are created based on the number of shared words between sentences. Differently from previous studies in multi-document summarization, we make a distinction between edges linking sentences from different documents (inter-layer) and those connecting sentences from the same document (intra-layer). As a proof of principle, our results reveal that such a discrimination between intra- and inter-layer in a multilayered representation is able to improve the quality of the generated summaries. This piece of information could be used to improve current statistical methods and related textual models. Highlights • A multilayer network model is proposed to address the extractive multidocument summarization task. • A differentiation between intra-layer and inter-layer edges allowed an improved representation of a set of documents. • Excellent performance was obtained for the PageRank measurement. • The proposed representation allows optimized results for both English and Portuguese languages. [ABSTRACT FROM AUTHOR]

In the last 16 years with the existence of Document Understanding Conference (DUC), several methods have been developed in Automatic Extractive Text Summarization (AETS) that have allowed the continuous improvement of this task. However, no significant analysis has been performed to determine the significance of the AETS methods. In this paper, we present a new method based on a Genetic Algorithm to determine the best sentence combination of DUC01 and DUC02 datasets to rank the newest methods of AETS. Using three heuristics presented in the state-of-the-art, we rank the most recent AETS methods, obtaining upper bounds and recovering lower bounds of the state-of-the-art. [ABSTRACT FROM AUTHOR]