Deep Reinforcement Learning with Distributional Semantic Rewards for Abstractive Summarization

2019-08-31 · IJCNLP 2019 11 · Siyao Li, Deren Lei, Pengda Qin, William Yang Wang

Deep reinforcement learning (RL) has been a commonly-used strategy for the abstractive summarization task to address both the exposure bias and non-differentiable task issues. However, the conventional reward Rouge-L simply looks for exact n-grams matches between candidates and annotated references, which inevitably makes the generated sentences repetitive and incoherent. In this paper, instead of Rouge-L, we explore the practicability of utilizing the distributional semantics to measure the matching degrees. With distributional semantics, sentence-level evaluation can be obtained, and semantically-correct phrases can also be generated without being limited to the surface form of the reference sentences. Human judgments on Gigaword and CNN/Daily Mail datasets show that our proposed distributional semantics reward (DSR) has distinct superiority in capturing the lexical and compositional diversity of natural language.

📄 PDF Abstract BibTeX arXiv:1909.00141

Code (0)

등록된 구현이 없습니다.

Tasks

Abstractive Text SummarizationDeep Reinforcement LearningDiversityreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Sentence

Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards

2021-07-01 · ACL 2021 5 · Shweta Yadav, Deepak Gupta, Asma Ben Abacha, Dina Demner-Fushman

The growth of online consumer health questions has led to the necessity for reliable and accurate question answering systems. A recent study showed that manual summarization of consumer health questions brings significan…

Question Answering Question Generation Question-Generation reinforcement-learning+2

Rewards with Negative Examples for Reinforced Topic-Focused Abstractive Summarization

2021-11-01 · EMNLP (newsum) 2021 11 · Khalil Mrini, Can Liu, Markus Dreyer

We consider the problem of topic-focused abstractive summarization, where the goal is to generate an abstractive summary focused on a particular topic, a phrase of one or multiple words. We hypothesize that the task of g…

Abstractive Text Summarization Deep Reinforcement Learning Reinforcement Learning (RL)

Using Question Answering Rewards to Improve Abstractive Summarization

2021-11-01 · Findings (EMNLP) 2021 11 · Chulaka Gunasekara, Guy Feigenblat, Benjamin Sznajder, Ranit Aharonov 외

Neural abstractive summarization models have drastically improved in the recent years. However, the summaries generated by these models generally suffer from issues such as: not capturing the critical facts in source doc…

Abstractive Text Summarization Question Answering

Generating Multiple-Length Summaries via Reinforcement Learning for Unsupervised Sentence Summarization

2022-12-21 · Dongmin Hyun, Xiting Wang, Chanyoung Park, Xing Xie 외

Sentence summarization shortens given texts while maintaining core contents of the texts. Unsupervised approaches have been studied to summarize texts without human-written summaries. However, recent unsupervised models …

Abstractive Text Summarization reinforcement-learning Reinforcement Learning (RL)Sentence+2

Inverse Reinforcement Learning for Text Summarization

2022-12-19 · Yu Fu, Deyi Xiong, Yue Dong

We introduce inverse reinforcement learning (IRL) as an effective paradigm for training abstractive summarization models, imitating human summarization behaviors. Our IRL model estimates the reward function using a suite…

Abstractive Text Summarization reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1