Papers › Summary Level Training of Sentence Rewriting for Abstractive Summarization

Summary Level Training of Sentence Rewriting for Abstractive Summarization

19 Sep 2019WS 2019 11arXiv:1909.08752archive 2025-07-28

Sanghwan Bae, Taeuk Kim, Jihoon Kim, Sang-goo Lee

As an attempt to combine extractive and abstractive summarization, Sentence Rewriting models adopt the strategy of extracting salient sentences from a document first and then paraphrasing the selected ones to generate a summary. However, the existing models in this framework mostly rely on sentence-level rewards or suboptimal labels, causing a mismatch between a training objective and evaluation metric. In this paper, we present a novel training signal that directly maximizes summary-level ROUGE scores through reinforcement learning. In addition, we incorporate BERT into our model, making good use of its ability on natural language understanding. In extensive experiments, we show that a combination of our proposed model and training procedure obtains new state-of-the-art performance on both CNN/Daily Mail and New York Times datasets. We also demonstrate that it generalizes better on DUC-2002 test set.

PaperPDFConference 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

Abstractive Text SummarizationExtractive Text SummarizationNatural Language UnderstandingReinforcement LearningSentenceSentence ReWriting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Abstractive Text Summarization CNN / Daily Mail BERT-ext + abs + RL + rerank ROUGE-1 41.90 #28 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail BERT-ext + abs + RL + rerank ROUGE-2 19.08 #28 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail BERT-ext + abs + RL + rerank ROUGE-L 39.64 #28 of 53 Archive leaderboard report
Extractive Text Summarization CNN / Daily Mail BERT-ext + RL ROUGE-1 42.76 #6 of 15 Archive leaderboard report
Extractive Text Summarization CNN / Daily Mail BERT-ext + RL ROUGE-2 19.87 #6 of 15 Archive leaderboard report
Extractive Text Summarization CNN / Daily Mail BERT-ext + RL ROUGE-L 39.11 #6 of 15 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.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

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