.png){kind=icon}
返回
Multi-Document Summarization Using Selective Attention Span and Reinforcement Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TASLP.2023.3316459.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The Abstractive text summarization systems using recently improved RNN-based sequence-to-sequence architecture have shown great promise for single-document summarization. However, such neural models fail to perpetuate the performance in the multi-document summarization setting owing to the long-range dependencies within the documents, overlapping/contradicting facts and extrinsic model hallucinations. These shortcomings augment the model to generate inconsistent, repetitive and non-factual summaries. In this work, we introduce REISA, a sequence-to-sequence model with a novel reinforced selective attention span that attends over the input and recalibrates the local attention weights to focus on important segments while generating output at each time step. REISA utilizes a reinforcement learning-based policy gradient algorithm to reward the model and formulate attention distributions over the encoder input. We further benchmark REISA on two widely-used multi-document summarization corpora - Multinews and CQASumm, and observe an improvement of +2.91 and +6.64 ROUGE-L scores, respectively. The qualitative analyses on semantic similarity by BERTScore, faithfulness by question-answer evaluation and human evaluation show significant improvement over the baseline-generated summaries.
Keyword:
Abstractive Text Summarization
Multi-Document Summarization
seq2seq
Deep Reinforcement Learning
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Some physicochemical parameters and 226Ra concentration in groundwater samples of North Guilan, Iran.png)
Chemosphere
ChemosphereIF0
PREAI
分享收藏Successful treatment with alectinib after crizotinib-induced interstitial lung disease克唑替尼诱发间质性肺疾病后阿来替尼的成功治疗Lung Cancer
Lung CancerIF0
PREAI
分享收藏Phase 0 clinical trials: theoretical and practical implications in oncologic drug developmentI期临床研究：肿瘤药物开发中的理论及实践意义
OAAI
OAAI分享收藏The powers of some tests of the equality of normal means against an ordered alternative正态均值相等性检验在有序备择假设下的功效Biometrika
BiometrikaIF0
PREAI
分享收藏
查看更多内容