Search

Pretrained models in abstractive summarization enable the summarization model to generate coherent summaries flexibly, but it also introduces unfactual hallucinations when generating novel words. To circumvent this drawback, we propose A Guided Tensor Product framework for abstractive Summarization (GTPSum). GTPSum utilizes highlighted sentence guidance signal and role embedding in the form of guided tensor product representations (GTPRs) to enhance the generation capacity for short document text. The guidance signal assists the model in focusing on crucial information, while the role embedding aids GTPSum in capturing the syntactic structure relationships present in the sentences. By employing this approach, the framework can not only focus on the essential information from the source document but also grasp the inherent sentence structure, resulting in generated summaries that closely align with the original content. The experimental results demonstrate the strong performance of our approach on the CNN/Daily Mail (44.28/20.88/41.08 ROUGE-1/-2/-L) and performed well on the other three datasets. Moreover, the comparison between our model generated summaries and those generated by the baseline models through human evaluation shows that our summaries contain more critical information, have better readability, and still maintain succinctness. [ABSTRACT FROM AUTHOR]

The purpose of government news summarization is to extract the most important information from official government news reports. It is important for readers to be able to understand government news quickly in the age of information overload. Compared with other types of news, government news reports have more detailed content and possess a more normative format, resulting in greater length. To resolve the contradiction between the length of these reports and the trend of fragmented reading, this research proposes an automatic text summarization model based on multiple features. First, the features are extracted using the TF–IDF algorithm and word vector embedding method based on the bidirectional encoder representation from the transformers model. Second, we score the sentences based on the position, keywords, and similarity features. Finally, the top-ranked sentence is selected to form the summarization. To verify the effectiveness and superiority of the proposed method, Edmundson and ROUGE were adopted. First, based on the Edmundson evaluation criteria, the summarization results of various methods were scored. The score differences between ATS summarization based on the proposed method and manual summarization were minimal across consistency, grammaticality, time sequence, conciseness, and readability, with values of 0.14, 0.18, 0.12, 0.10, and 0.16, respectively. This suggests that our summarization exhibits the highest similarity to manual summarization. Second, we evaluated the summarization results using the ROUGE evaluation criteria. The results indicate that the proposed method achieved significantly higher scores compared to other models. Specifically, for character-level ROUGE-1, the P, R, and F scores reached 0.84, 0.93, and 0.88, respectively. At the word-level ROUGE-1, the P, R, and F scores were 0.81, 0.89, and 0.85, respectively, which demonstrates a noticeable improvement over other models. Furthermore, compared to manual methods, the proposed method has advantages in assisting the reader to obtain important information rapidly. [ABSTRACT FROM AUTHOR]

Many enterprise systems are document-intensive and require extensive manual verification. The verification process has challenge in terms of time and remaining bugs. A general automatic or semi-automatic document verification system would be useful. However, as the nature of the natural language, the context is an important factor. In this research, the target context is selected to be the financial documents, which have been highly interested recently. An automatic document verification model based on only entities (mostly faced within financial documents) was experimented. The summary report was verified with original documents, such that entities in the summary were searched for matching in the original documents. Verification process success was evaluated by comparison of the named entity algorithms in the literature. The special Kaggle data set ready for this purpose was used for entity matching from the summary within the original documents. The average document verification accuracy of named entity finding algorithms for only financial type documents was 85.36%, where the proposed entity recognition algorithm reached 88.80%. On the other hand, the average document verification time of the experimented algorithms and the developed algorithm is 2.43 and 2.48 s respectively. As a conclusion, when both the BERT-base-cased classification model and rule-based approaches are applied specific to the context, it enhances the entity verification process with an insignificant time cost. Consequently, even we used limited data and rules, it is seen that there exists opportunity to automatize the document verification process with the support of both the BERT-base-cased classification model and rule-based approaches. [ABSTRACT FROM AUTHOR]

Unsupervised opinion summarization is the technique of automatically generates summaries without gold reference, and the summaries that reflects aspects of information about the entity. Although there are more mature studies on unsupervised opinion summarazaiton, but these studies focus more on unsupervised training methods and ignore the extraction of information by the model. In this paper, we propose JointSum, an unsupervised opinion summarization method based on variational autoencoder model. JointSum first extracts aspect and sentiment information in reviews by joint attention and dictionary learning, respectively. Joint attention consists of text attention and auxiliary attention, which can extract key information in the input text from different fine-grained levels. Then we calculate the variance and mean of the Gaussian distribution in variational autoencoder model using aspect and sentiment information. In addition, we added the review score prediction subtask to increase the robustness of the model. Finally, in generation phase, we adopt pointer-generator network because it includes copy and coverage mechanism that can solve problems in text generation. Experiments on Amazon and Yelp datasets, the results show that the model has good performance in both automatic and human evaluation, the ROUGE-L value on the Yelp dataset gets 20.83. [ABSTRACT FROM AUTHOR]

The number of research articles published on COVID-19 has dramatically increased since the outbreak of the pandemic in November 2019. This absurd rate of productivity in research articles leads to information overload. It has increasingly become urgent for researchers and medical associations to stay up to date on the latest COVID-19 studies. To address information overload in COVID-19 scientific literature, the study presents a novel hybrid model named CovSumm, an unsupervised graph-based hybrid approach for single-document summarization, that is evaluated on the CORD-19 dataset. We have tested the proposed methodology on the scientific papers in the database dated from January 1, 2021 to December 31, 2021, consisting of 840 documents in total. The proposed text summarization is a hybrid of two distinctive extractive approaches (1) GenCompareSum (transformer-based approach) and (2) TextRank (graph-based approach). The sum of scores generated by both methods is used to rank the sentences for generating the summary. On the CORD-19, the recall-oriented understudy for gisting evaluation (ROUGE) score metric is used to compare the performance of the CovSumm model with various state-of-the-art techniques. The proposed method achieved the highest scores of ROUGE-1: 40.14%, ROUGE-2: 13.25%, and ROUGE-L: 36.32%. The proposed hybrid approach shows improved performance on the CORD-19 dataset when compared to existing unsupervised text summarization methods. [ABSTRACT FROM AUTHOR]

Considering the huge volume of opinion texts published on various social networks, it is extremely difficult to peruse and use these texts. The automatic creation of summaries can be a significant help for the users of such texts. The current paper employs manifold learning to mitigate the challenges of the complexity and high dimensionality of opinion texts and the K-Means algorithm for clustering. Furthermore, summarization based on the concepts of the texts can improve the performance of the summarization system. The proposed method is unsupervised extractive, and summarization is performed based on the concepts of the texts using the multi-objective pruning approach. The main parameters utilized to perform multi-objective pruning include relevancy, redundancy, and coverage. The simulation results show that the proposed method outperformed the MOOTweetSumm method while providing an improvement of 11% in terms of the ROGUE-1 measure and an improvement of 9% in terms of the ROGUE-L measure. [ABSTRACT FROM AUTHOR]

The difficulty of deriving value out of vast available scientific literature in a condensed form lead us to look for a proficient theme based summarization solution which can preserve precise biomedical content. The study targets to analyze impact of combining semantic biomedical concepts extraction, frequent item-set mining and clustering techniques over information retention, objective functions and ROUGE values for the obtained final summary. The suggested frequent item-set mining and clustering (FRI-CL) graph-based framework uses UMLS metathesarus and BERT-based semantic embeddings to identify domain-relevant concepts. The scrutinized concepts are mined according to their relationship with neighbors and frequency via an amended FP-Growth model. The framework utilizes S-DPMM clustering, which is a probabilistic mixture model and aids in the identification and clubbing of complex relevant patterns to increase coverage of important sub-themes. The sentences with the frequent concepts are scored via PageRank to form an efficient and compelling summary. The research experiments on the 100 sample biomedical documents taken from PubMed archives are evaluated via calculation of ROUGE scores, coverage, readability, non-redundancy, memory utilization and information retention from the summary output. The results with the FRI-CL summarization system showcased 10% ROUGE performance improvement and are at par with the other baseline methods. On an average 30–40% improvement in memory utilization is observed with up to 50% information retention when experiments are performed using S-DPMM clustering. The research indicates that the fusion of semantic mapping, clustering, along with frequent-item set mining of biomedical concepts enhance the overall co-related information covering all sub-themes. [ABSTRACT FROM AUTHOR]