An Editorial Network for Enhanced Document Summarization

Moroshko, Edward; Feigenblat, Guy; Roitman, Haggai; Konopnicki, David

doi:10.18653/v1/d19-5407

Cited by 9 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later, Chen and Bansal [2] proposed a hybrid extractive-abstractive architecture via a policy-based reinforcement learning method, which optimizes the ROUGE evaluation between the extracted sentences and the reference summary. As expected, these methods [2,6,13,21] have ability to generate fluent summaries. Like other supervised summarization methods, they focus on matching generated summary and reference summary.…”

Section: Related Worksupporting

confidence: 71%

Reinforcing Semantic-Symmetry for Document Summarization

Song¹,

Jing²

2021

Preprint

View full text Add to dashboard Cite

Document summarization condenses a long document into a short version with salient information and accurate semantic descriptions. The main issue is how to make the output summary semantically consistent with the input document. To reach this goal, recently, researchers have focused on supervised end-to-end hybrid approaches, which contain an extractor module and abstractor module. Among them, the extractor identifies the salient sentences from the input document, and the abstractor generates a summary from the salient sentences. This model successfully keeps the consistency between the generated summary and the reference summary via various strategies (e.g., reinforcement learning). There are two semantic gaps when training the hybrid model (one is between document and extracted sentences, and the other is between extracted sentences and summary). However, they are not explicitly considered in the existing methods, which usually results in a semantic bias of summary. To mitigate the above issue, in this paper, a new reinforcing semantic-symmetry learning model is proposed for document summarization (ReSyM). ReSyM introduces a semantic-consistency reward in the extractor to bridge the first gap. A semantic dual-reward is designed to bridge the second gap in the abstractor. The whole document summarization process is implemented via reinforcement learning with a hybrid reward mechanism (combining the above two rewards). Moreover, a comprehensive sentence representation learning method is presented to sufficiently capture the information from the original document. A series of experiments have been conducted on two wildly used benchmark datasets CNN/Daily Mail and BigPatent. The results have shown the superiority of ReSyM by comparing it with the state-of-the-art baselines in terms of various evaluation metrics.

show abstract

Section: Related Worksupporting

confidence: 71%

Reinforcing Semantic-Symmetry for Document Summarization

Song¹,

Jing²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“… Bottom-Up [ 141 ]: a novel Seq2seq summarization that utilizes a bottom-up attention as a selector to select salient sentences. EditNet [ 143 ]: a mixed extractive-abstractive model that utilizes an editorial network to generate summary. Two-Stage + RL [ 144 ]: a novel Seq2seq pretrained framework that employs a two-stage decoder to generate summary.…”

Section: Performance Analysismentioning

confidence: 99%

“…EditNet [ 143 ]: a mixed extractive-abstractive model that utilizes an editorial network to generate summary.…”

Section: Performance Analysismentioning

confidence: 99%

A Comprehensive Survey of Abstractive Text Summarization Based on Deep Learning

Zhang¹,

Zhou²,

Yu³

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the rapid development of the Internet, the massive amount of web textual data has grown exponentially, which has brought considerable challenges to downstream tasks, such as document management, text classification, and information retrieval. Automatic text summarization (ATS) is becoming an extremely important means to solve this problem. The core of ATS is to mine the gist of the original text and automatically generate a concise and readable summary. Recently, to better balance and develop these two aspects, deep learning (DL)-based abstractive summarization models have been developed. At present, for ATS tasks, almost all state-of-the-art (SOTA) models are based on DL architecture. However, a comprehensive literature survey is still lacking in the field of DL-based abstractive text summarization. To fill this gap, this paper provides researchers with a comprehensive survey of DL-based abstractive summarization. We first give an overview of abstractive summarization and DL. Then, we summarize several typical frameworks of abstractive summarization. After that, we also give a comparison of several popular datasets that are commonly used for training, validation, and testing. We further analyze the performance of several typical abstractive summarization systems on common datasets. Finally, we highlight some open challenges in the abstractive summarization task and outline some future research trends. We hope that these explorations will provide researchers with new insights into DL-based abstractive summarization.

show abstract

“…With the development of large-scale summarization datasets such as CNN/DailyMail (Hermann et al, 2015), NYT (Sandhaus, 2008), Newsroom (Grusky et al, 2018) and XSum (Narayan et al, 2018a), along with advancements in deep neural-based architectures, modern supervised neural network-based methods that employ encoderdecoder framework have become increasingly popular. These models have been proposed with extractive strategies (Cheng and Lapata, 2016;Nallapati et al, 2017;Wu and Hu, 2018;Dong et al, 2018;Zhou et al, 2018;Narayan et al, 2018b); abstractive strategies (See et al, 2017;Chen and Bansal, 2018;Gehrmann et al, 2018;Zhang et al, 2019a;Lewis et al, 2019); and hybrid strategies (Hsu et al, 2018;Bae et al, 2019;Moroshko et al, 2019).…”

Section: Extractive Summarizationmentioning

confidence: 99%

Discourse-Aware Unsupervised Summarization for Long Scientific Documents

Dong¹,

Romascanu²,

Cheung³

2021

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

View full text Add to dashboard Cite

We propose an unsupervised graph-based ranking model for extractive summarization of long scientific documents. Our method assumes a two-level hierarchical graph representation of the source document, and exploits asymmetrical positional cues to determine sentence importance. Results on the PubMed and arXiv datasets show that our approach 1 outperforms strong unsupervised baselines by wide margins in automatic metrics and human evaluation. In addition, it achieves performance comparable to many state-of-the-art supervised approaches which are trained on hundreds of thousands of examples. These results suggest that patterns in the discourse structure are a strong signal for determining importance in scientific articles. * Equal contribution. 1 Link to our code: https://github.com/ mirandrom/HipoRank. Introductionanxiety affects quality of life in those living with parkinson's disease (pd) more so than overall cognitive status, motor deficits, apathy, and depression.

show abstract

An Editorial Network for Enhanced Document Summarization

Cited by 9 publications

References 24 publications

Reinforcing Semantic-Symmetry for Document Summarization

Reinforcing Semantic-Symmetry for Document Summarization

A Comprehensive Survey of Abstractive Text Summarization Based on Deep Learning

Discourse-Aware Unsupervised Summarization for Long Scientific Documents

Contact Info

Product

Resources

About