Papers › Learning to Extract Coherent Summary via Deep Reinforcement Learning

Learning to Extract Coherent Summary via Deep Reinforcement Learning

19 Apr 2018arXiv:1804.07036archive 2025-07-28

Yuxiang Wu, Baotian Hu

Coherence plays a critical role in producing a high-quality summary from a document. In recent years, neural extractive summarization is becoming increasingly attractive. However, most of them ignore the coherence of summaries when extracting sentences. As an effort towards extracting coherent summaries, we propose a neural coherence model to capture the cross-sentence semantic and syntactic coherence patterns. The proposed neural coherence model obviates the need for feature engineering and can be trained in an end-to-end fashion using unlabeled data. Empirical results show that the proposed neural coherence model can efficiently capture the cross-sentence coherence patterns. Using the combined output of the neural coherence model and ROUGE package as the reward, we design a reinforcement learning method to train a proposed neural extractive summarizer which is named Reinforced Neural Extractive Summarization (RNES) model. The RNES model learns to optimize coherence and informative importance of the summary simultaneously. Experimental results show that the proposed RNES outperforms existing baselines and achieves state-of-the-art performance in term of ROUGE on CNN/Daily Mail dataset. The qualitative evaluation indicates that summaries produced by RNES are more coherent and readable.

Paper PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Deep Reinforcement Learning Extractive Summarization Feature Engineering Reinforcement Learning Reinforcement Learning (RL)Sentence Text Summarization reinforcement-learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Text Summarization	CNN / Daily Mail (Anonymized)	RNES w/o coherence	ROUGE-1	41.25	#3 of 13	Archive leaderboard	report
Text Summarization	CNN / Daily Mail (Anonymized)	RNES w/o coherence	ROUGE-2	18.87	#3 of 13	Archive leaderboard	report
Text Summarization	CNN / Daily Mail (Anonymized)	RNES w/o coherence	ROUGE-L	37.75	#3 of 13	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections