Unsupervised Sentence Enhancement for Automatic Summarization

Cheung, Jackie Chi Kit; Penn, Gerald

doi:10.3115/v1/d14-1085

Cited by 28 publications

(12 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Gerani et al, 2014) generate abstractive summaries by modifying discourse parse trees. Our work is similar in spirit to Cheung and Penn (2014), which splices and recombines dependency parse trees to produce abstractive summaries. In contrast, our work operates on semantic graphs, taking advantage of the recently developed AMR Bank.…”

Section: Related and Future Workmentioning

confidence: 99%

Toward Abstractive Summarization Using Semantic Representations

Liu¹,

Flanigan²,

Thomson³

et al. 2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

189

181

View full text Add to dashboard Cite

We present a novel abstractive summarization framework that draws on the recent development of a treebank for the Abstract Meaning Representation (AMR). In this framework, the source text is parsed to a set of AMR graphs, the graphs are transformed into a summary graph, and then text is generated from the summary graph. We focus on the graph-tograph transformation that reduces the source semantic graph into a summary graph, making use of an existing AMR parser and assuming the eventual availability of an AMR-totext generator. The framework is data-driven, trainable, and not specifically designed for a particular domain. Experiments on goldstandard AMR annotations and system parses show promising results. Code is available at: https://github.com/summarization

show abstract

Section: Related and Future Workmentioning

confidence: 99%

Toward Abstractive Summarization Using Semantic Representations

Liu¹,

Flanigan²,

Thomson³

et al. 2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

189

181

View full text Add to dashboard Cite

show abstract

“…Earlier summarization work was based on extraction and compression-based approaches (Jing, 2000;Knight and Marcu, 2002;Clarke and Lapata, 2008;Filippova et al, 2015), with more focus on graph-based (Giannakopoulos, 2009;Ganesan et al, 2010) and discourse tree-based (Gerani et al, 2014) models. Recent focus has shifted towards abstractive, rewriting-based summarization based on parse trees (Cheung and Penn, 2014;Wang et al, 2016), Abstract Meaning Representations (Liu et al, 2015;Dohare and Karnick, 2017), and neural network models with pointercopy mechanism and coverage (Rush et al, 2015;Chopra et al, 2016;Nallapati et al, 2016;See et al, 2017), as well as reinforcebased metric rewards (Ranzato et al, 2015;Paulus et al, 2017). We also use reinforce-based models, but with novel reward functions and better simultaneous multi-reward optimization methods.…”

Section: Related Workmentioning

confidence: 99%

Multi-Reward Reinforced Summarization with Saliency and Entailment

Pasunuru¹,

Bansal²

2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

135

140

View full text Add to dashboard Cite

Abstractive text summarization is the task of compressing and rewriting a long document into a short summary while maintaining saliency, directed logical entailment, and nonredundancy. In this work, we address these three important aspects of a good summary via a reinforcement learning approach with two novel reward functions: ROUGESal and Entail, on top of a coverage-based baseline. The ROUGESal reward modifies the ROUGE metric by up-weighting the salient phrases/words detected via a keyphrase classifier. The Entail reward gives high (length-normalized) scores to logically-entailed summaries using an entailment classifier. Further, we show superior performance improvement when these rewards are combined with traditional metric (ROUGE) based rewards, via our novel and effective multi-reward approach of optimizing multiple rewards simultaneously in alternate mini-batches. Our method achieves the new state-of-the-art results (including human evaluation) on the CNN/Daily Mail dataset as well as strong improvements in a test-only transfer setup on DUC-2002.

show abstract

“…Automatic text summarization has been progressively improving over the time, initially more focused on extractive and compressive models (Jing and McKeown, 2000;Knight and Marcu, 2002;Clarke and Lapata, 2008;Filippova et al, 2015;Kedzie et al, 2015), and moving more towards compressive and abstractive summarization based on graphs and concept maps (Giannakopoulos, 2009;Ganesan et al, 2010;Falke and Gurevych, 2017) and discourse trees (Gerani et al, 2014), syntactic parse trees (Cheung and Penn, 2014;Wang et al, 2013), and Abstract Meaning Representations (AMR) (Liu et al, 2015;Dohare and Karnick, 2017). Recent work has also adopted machine translation inspired neural seq2seq models for abstractive summarization with advances in hierarchical, distractive, saliency, and graphattention modeling (Rush et al, 2015;Chopra et al, 2016;Nallapati et al, 2016;Chen et al, 2016;Tan et al, 2017).…”

Section: Related Workmentioning

confidence: 99%

Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation

Guo

Pasunuru

Bansal

2018

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

137

106

View full text Add to dashboard Cite

An accurate abstractive summary of a document should contain all its salient information and should be logically entailed by the input document. We improve these important aspects of abstractive summarization via multi-task learning with the auxiliary tasks of question generation and entailment generation, where the former teaches the summarization model how to look for salient questioning-worthy details, and the latter teaches the model how to rewrite a summary which is a directed-logical subset of the input document. We also propose novel multitask architectures with high-level (semantic) layer-specific sharing across multiple encoder and decoder layers of the three tasks, as well as soft-sharing mechanisms (and show performance ablations and analysis examples of each contribution). Overall, we achieve statistically significant improvements over the state-ofthe-art on both the CNN/DailyMail and Gigaword datasets, as well as on the DUC-2002 transfer setup. We also present several quantitative and qualitative analysis studies of our model's learned saliency and entailment skills. rian, and Claire Cardie. 2013. A sentence compression based framework to query-focused multidocument summarization. In ACL.Matthew D Zeiler and Rob Fergus. 2014. Visualizing and understanding convolutional networks. In European conference on computer vision, pages 818-833. Springer.

show abstract

Unsupervised Sentence Enhancement for Automatic Summarization

Cited by 28 publications

References 11 publications

Toward Abstractive Summarization Using Semantic Representations

Toward Abstractive Summarization Using Semantic Representations

Multi-Reward Reinforced Summarization with Saliency and Entailment

Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation

Contact Info

Product

Resources

About