Search

Whenever there is too much information out there, it is desirable to summarize. If humans are trying to create the summary, it will take lot of time. Now to make the problem of summarizing information easier and more effortless one can automate the summarization process which can reduce the time taken in creating summary. This is called as automatic summarization. The two ways of summarization are extractive summarization and abstractive summarization. Extractive summarization and its applications have been the subject of extensive research and have received state of art solution. But abstractive summarization still is a progressive field as it is difficult to create abstractive summary as humans do. Also, it is still a question i.e., how to evaluate the quality of a summary? Therefore, this paper is a comprehensive survey on the dataset used with its details and statistics, analysis of various abstractive summarization techniques and important parameters for evaluating the quality of summary. Deep leaning based models have given new direction in this field. The author also focuses on problems and challenges faced in the generation of summary which are opening the future research scope in this domain. [ABSTRACT FROM AUTHOR]

In recent years, deep learning has revolutionized natural language processing (NLP) by enabling the development of models that can learn complex representations of language data, leading to significant improvements in performance across a wide range of NLP tasks. Deep learning models for NLP typically use large amounts of data to train deep neural networks, allowing them to learn the patterns and relationships in language data. This is in contrast to traditional NLP approaches, which rely on hand-engineered features and rules to perform NLP tasks. The ability of deep neural networks to learn hierarchical representations of language data, handle variable-length input sequences, and perform well on large datasets makes them well-suited for NLP applications. Driven by the exponential growth of textual data and the increasing demand for condensed, coherent, and informative summaries, text summarization has been a critical research area in the field of NLP. Applying deep learning to text summarization refers to the use of deep neural networks to perform text summarization tasks. In this survey, we begin with a review of fashionable text summarization tasks in recent years, including extractive, abstractive, multi-document, and so on. Next, we discuss most deep learning-based models and their experimental results on these tasks. The paper also covers datasets and data representation for summarization tasks. Finally, we delve into the opportunities and challenges associated with summarization tasks and their corresponding methodologies, aiming to inspire future research efforts to advance the field further. A goal of our survey is to explain how these methods differ in their requirements as understanding them is essential for choosing a technique suited for a specific setting. This survey aims to provide a comprehensive review of existing techniques, evaluation methodologies, and practical applications of automatic text summarization. [ABSTRACT FROM AUTHOR]

Fine-tuning a pre-trained sequence-to-sequence-based language model has significantly advanced the field of abstractive summarization. However, the early models of abstractive summarization were limited by the gap between training and inference, and they did not fully utilize the potential of the language model. Recent studies have introduced a two-stage framework that allows the second-stage model to re-rank the candidate summary generated by the first-stage model, to resolve these limitations. In this study, we point out that the supervision method performed in the existing re-ranking model of the two-stage abstractive summarization framework cannot learn detailed and complex information of the data. In addition, we present the problem of positional bias in the existing encoder–decoder-based re-ranking model. To address these two limitations, this study proposes a hierarchical supervision method that jointly performs summary and sentence-level supervision. For sentence-level supervision, we designed two sentence-level loss functions: intra- and inter-intra-sentence ranking losses. Compared to the existing abstractive summarization model, the proposed method exhibited a performance improvement for both the CNN/DM and XSum datasets. The proposed model outperformed the baseline model under a few-shot setting. [ABSTRACT FROM AUTHOR]

Recently, for the abstractive summarization task, most of proposed techniques have adopted the deep recurrent neural network (RNN)-based sequential auto-encoding architecture to effectively learn and generate meaningful summaries for different input documents. However, most of recent RNN-based models always suffer the challenges related to the involvement of much capturing high-frequency/reparative phrases in long documents during the training process which leads to the outcome of trivial and generic summaries are generated. In addition, the lack of thorough analysis on the sequential and long-range dependency relationships between words within different contexts while learning the textual representation also makes the achieved summaries unnatural and incoherent. In order to deal with these challenges, in this paper we proposed a novel semantic-enhanced generative adversarial network (GAN)-based approach for abstractive text summarization task, called as: SGAN4AbSum. We use an adversarial training strategy for our text summarization model which trains the generator and discriminator to simultaneously handle the summary generation and distinguishing the generated summary with the ground-truth one. The input of generator is the jointed rich-semantic and global structural latent representations of training documents which are achieved by applying a combined BERT and graph convolutional network textual embedding mechanism. Extensive experiments in benchmark datasets demonstrate the effectiveness of our proposed SGAN4AbSum which achieve the competitive ROUGE-based scores in comparing with state-of-the-art abstractive text summarization baselines. [ABSTRACT FROM AUTHOR]

Long document summarization poses obstacles to current generative transformer-based models because of the broad context to process and understand. Indeed, detecting long-range dependencies is still challenging for today's state-of-the-art solutions, usually requiring model expansion at the cost of an unsustainable demand for computing and memory capacities. This paper introduces Emma, a novel efficient memory-enhanced transformer-based architecture. By segmenting a lengthy input into multiple text fragments, our model stores and compares the current chunk with previous ones, gaining the capability to read and comprehend the entire context over the whole document with a fixed amount of GPU memory. This method enables the model to deal with theoretically infinitely long documents, using less than 18 and 13 GB of memory for training and inference, respectively. We conducted extensive performance analyses and demonstrate that Emma achieved competitive results on two datasets of different domains while consuming significantly less GPU memory than competitors do, even in low-resource settings. [ABSTRACT FROM AUTHOR]

Text summarization on non-factoid question answering (NQA) aims at identifying the core information of redundant answer guidance using questions, which can dramatically improve answer readability and comprehensibility. Most existing approaches focus on extracting query-related sentences to construct a summary, where the logical connection of natural language and the hierarchical interpretable semantic association are often neglected, thus degrading performance. To address these issues, we propose a novel question-driven abstractive answer summarization model, called the Hierarchical Sliding Inference Generator (HSIG), to form inferable and interpretable summaries by explicitly introducing hierarchical information reasoning between questions and corresponding answers. Specifically, we first apply an elaborately designed hierarchical sliding fusion inference model to determine the most relevant question sentence-level representation that provides a deeper interpretable basis for sentence selection in summarization, which further increases computational performance on the premise of following the semantic inheritance structure. Additionally, to improve summary fluency, we construct a double-driven selective generator to integrate various semantic information from two mutual question-and-answer perspectives. Experimental results illustrate that compared with stateof-the-art baselines, our model achieves remarkable improvement on two benchmark datasets and specifically improves the 2.46 ROUGE-1 points on PubMedQA, which demonstrates the superiority of our model on abstractive summarization with hierarchical sequential reasoning. [ABSTRACT FROM AUTHOR]

Today, timestamped web documents related to a general news query flood the Internet, and timeline summarization targets this concisely by summarizing the evolution trajectory of events along the timeline. Unlike traditional document summarization, timeline summarization needs to model the time series information of the input events and summarize important events in chronological order. To tackle this challenge, in this article we propose our Unified Timeline Summarizer, which can generate abstractive and extractive timeline summaries in time order. Concretely, in the encoder part, we propose a graph-based event encoder that relates multiple events according to their content dependency and learns a global representation of each event. In the decoder part, to ensure the chronological order of the abstractive summary, we propose to extract the feature of event-level attention in its generation process with sequential information retained and use it to simulate the evolutionary attention of the ground truth summary. The event-level attention can also be used to assist in extracting a summary, where the extracted summary also comes in time sequence. We augment the previous Chinese large-scale timeline summarization dataset and collect a new English timeline dataset. Extensive experiments conducted on these datasets and on the out-of-domain Timeline 17 dataset show that our Unified Timeline Summarizer achieves state-of-the-art performance in terms of both automatic and human evaluations. [ABSTRACT FROM AUTHOR]

The main task of our research is to train various abstractive summarization models for the Arabic language. The work for abstractive Arabic text summarization has hardly begun so far due to the unavailability of the datasets needed for that. In our previous research, we created the first monolingual corpus in the Arabic language for abstractive text summarization. Based on this corpus, we fine-tuned various transformer models. We tested the PreSumm and multilingual BART models. We achieved a "state of the art" result in this area with the PreSumm method. The present study continues the same series of research. We extended our corpus "AraSum" and managed to reach up to 50 thousand items, each consisting of an article and its corresponding lead. In addition, we pretrained our own monolingual and trilingual BART models for the Arabic language and fine-tuned them in addition to the mT5 model for abstractive text summarization for the same language, using the AraSum corpus. While there is room for improvement in the resources and the infrastructure we possess, the results clearly demonstrate that most of our models surpassed the XL-Sum which is considered to be state of the art for abstractive Arabic text summarization so far. Our corpus "AraSum" will be released to facilitate future work on abstractive Arabic text summarization. [ABSTRACT FROM AUTHOR]

Generative ability is a crucial need for artificial intelligence applications, such as chatbots, virtual assistants, machine translation systems etc. In recent years, the transformer-based neural architectures gave a huge boost to generate human-like English texts. In our research we did experiments to create pre-trained generative transformer models for Hungarian language and fine-tune them for multiple types of natural language processing tasks. In our focus, multilingual models were trained. We have pre-trained a multilingual BART, then fine-tuned it to various NLP tasks, such as text classification, abstractive summarization. In our experiments, we focused on transfer learning techniques to increase the performance. Furthermore, a M2M100 multilingual model was fine-tuned for a 12-lingual Hungarian- Centric machine translation. Last but not least, a Marian NMT based machine translation system was also built from scratch for the 12-lingual Hungarian-Centric machine translation task. In our results, using the cross-lingual transfer method we could achieve higher performance in all of our tasks. In our machine translation experiment, using our fine-tuned M2M100 model we could outperform the Google Translate, Microsoft Translator and eTranslation. [ABSTRACT FROM AUTHOR]

It is important for abstractive summarization models to understand the important parts of the original document and create a natural summary accordingly. Recently, studies have been conducted to incorporate important parts of the original document during learning and have shown good performance. However, these studies are effective for explicit datasets but not implicit datasets which are relatively more abstract. This study addresses the challenge of summarizing implicit datasets, which have a lower deviation in the significance of important sentences compared to explicit datasets. A multi-task learning approach that reflects information about salient and incidental objects during the learning process was proposed. This was achieved by adding a contrastive objective to the fine-tuning process of the encoder-decoder language model. The salient and incidental parts were selected based on the ROUGE-L F1 score and their relationships were learned through triplet loss. The proposed method was evaluated using five benchmark summarization datasets, including two explicit and three implicit. The experimental results showed a greater improvement in implicit datasets, particularly for the highly abstractive XSum dataset, compared to the vanilla fine-tuning method in both the BART-base and T5-small models. [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]

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]

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]

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]

The problem of factual incorrectness in machine-generated abstractive summarization has received widespread attention in the past few years. Although large-scale neural models show excellent capability in generating fluent and coherent summaries, they still struggle with factual inconsistency, in which the named entity incorrectness is the most frequent and notable one, especially for the character-based languages, such as Chinese. Since abstractive summaries are mostly generated character by character in Chinese, the problem of hallucinated entities is more severe than that of other word-based languages. In this paper, we propose CC-Gens, a novel approach for Correctness Checking based on a Generative negative sampling strategy. Considering that the problem is due to the uncertain nature of the language generation process, we leverage fine-tuned generative language models, i.e., UniLMv2 and mT5, to generate summaries with incorrect entities, thereby constructing a synthetic binary classification dataset for the factuality discriminative model. We propose three strategies: Entity Sampling, Sequence Sampling, and Cloze Sampling, to generate summaries with incorrect entities. With such strategies, the negative samples are much more similar in nature to the output of the neural summarization model. We then train a BERT-based discriminator to identify factually incorrect machine-generated summaries with entity errors based on these generative negative samples. We further propose a novel PU learning algorithm to improve the performance of our approach by iteratively training the discriminator to select high confident negative samples from the unlabeled model generated summaries to replace the former artificially constructed ones. By generating multiple candidate summaries and selecting the one with the highest factual correctness score among them, our approach can significantly reduce the probability that an output summary contains factual errors. According to a comprehensive evaluation, the CC-Gens we proposed outperforms previous works in identifying faithless summaries as well as providing faithful ones. [Display omitted] • Named entity error ratio in Chinese abstractive summaries is as high as 58.1%. • We propose generative negative sampling strategies for training the discriminator. • We apply PU learning to improve performance by selecting high-confident samples. [ABSTRACT FROM AUTHOR]