Papers › Concept Pointer Network for Abstractive Summarization

Concept Pointer Network for Abstractive Summarization

18 Oct 2019IJCNLP 2019 11arXiv:1910.08486archive 2025-07-28

Wang Wenbo, Gao Yang, Huang Heyan, Zhou Yuxiang

A quality abstractive summary should not only copy salient source texts as summaries but should also tend to generate new conceptual words to express concrete details. Inspired by the popular pointer generator sequence-to-sequence model, this paper presents a concept pointer network for improving these aspects of abstractive summarization. The network leverages knowledge-based, context-aware conceptualizations to derive an extended set of candidate concepts. The model then points to the most appropriate choice using both the concept set and original source text. This joint approach generates abstractive summaries with higher-level semantic concepts. The training model is also optimized in a way that adapts to different data, which is based on a novel method of distantly-supervised learning guided by reference summaries and testing set. Overall, the proposed approach provides statistically significant improvements over several state-of-the-art models on both the DUC-2004 and Gigaword datasets. A human evaluation of the model's abstractive abilities also supports the quality of the summaries produced within this framework.

PaperPDFConference PDFCode

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

Code

wprojectsn/codes officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Abstractive Text SummarizationText Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Summarization GigaWord Concept pointer+RL ROUGE-1 38.02 #22 of 41 Archive leaderboard report
Text Summarization GigaWord Concept pointer+RL ROUGE-2 16.97 #22 of 41 Archive leaderboard report
Text Summarization GigaWord Concept pointer+RL ROUGE-L 35.43 #22 of 41 Archive leaderboard report
Text Summarization GigaWord Concept pointer+DS ROUGE-1 37.01 #27 of 41 Archive leaderboard report
Text Summarization GigaWord Concept pointer+DS ROUGE-2 17.1 #27 of 41 Archive leaderboard report
Text Summarization GigaWord Concept pointer+DS ROUGE-L 34.87 #27 of 41 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

LSTMPointer NetworkSigmoid ActivationSoftmaxTanh Activation

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