ABSTRACT
In this paper, we study abstractive review summarization. Observing that review summaries often consist of aspect words, opinion words and context words, we propose a two-stage reinforcement learning approach, which first predicts the output word type from the three types, and then leverages the predicted word type to generate the final word distribution. Experimental results on two Amazon product review datasets demonstrate that our method can consistently outperform several strong baseline approaches based on ROUGE scores.
- Stefanos Angelidis and Mirella Lapata. 2018. Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised. In Proceedings of EMNLP.Google ScholarCross Ref
- John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research 12, Jul (2011), 2121--2159.Google ScholarDigital Library
- Kavita Ganesan, ChengXiang Zhai, and Jiawei Han. 2010. Opinosis: A graph based approach to abstractive summarization of highly redundant opinions. In Proceedings of COLING.Google Scholar
- Shima Gerani, Yashar Mehdad, Giuseppe Carenini, Raymond T Ng, and Bita Nejat. 2014. Abstractive summarization of product reviews using discourse structure. In Proceedings of EMNLP. 1602--1613.Google ScholarCross Ref
- J Gu, Z Lu, H Li, and VOK Li. 2016. Incorporating copying mechanism in sequenceto- sequence learning. In Proceedings of ACL.Google Scholar
- Eric Jang, Shixiang Gu, and Ben Poole. 2016. Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016).Google Scholar
- Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out: Proceedings of the ACL-04 Workshop.Google Scholar
- Ramesh Nallapati, Bowen Zhou, Caglar Gulcehre, Bing Xiang, et al. 2016. Abstractive text summarization using sequence-to-sequence rnns and beyond. arXiv preprint arXiv:1602.06023 (2016).Google Scholar
- Guang Qiu, Bing Liu, Jiajun Bu, and Chun Chen. 2011. Opinion word expansion and target extraction through double propagation. Computational linguistics 37, 1 (2011), 9--27.Google Scholar
- Abigail See, Peter J Liu, and Christopher D Manning. 2017. Get to the point: Summarization with pointer-generator networks. In Proceedings of ACL.Google Scholar
- Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. 2015. Pointer networks. In Proceedings of NIPS.Google Scholar
- Lu Wang and Wang Ling. 2016. Neural Network-Based Abstract Generation for Opinions and Arguments. In Proceedings of NAACL-HLT.Google ScholarCross Ref
- Yansen Wang, Chenyi Liu, Minlie Huang, and Liqiang Nie. 2018. Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders. In Proceedings of ACL.Google ScholarCross Ref
- Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning 8, 3--4 (1992), 229--256.Google Scholar
- Min Yang, Qiang Qu, Ying Shen, Qiao Liu,Wei Zhao, and Jia Zhu. 2018. Aspect and sentiment aware abstractive review summarization. In Proceedings of COLING.Google Scholar
- Min Yang, Qiang Qu, Jia Zhu, and et al. 2018. Cross-domain Aspect/Sentimentaware Abstractive Review Summarization. In Proceedings of CIKM.Google Scholar
Index Terms
- Aspect and Opinion Aware Abstractive Review Summarization with Reinforced Hard Typed Decoder
Recommendations
Sentiment diversification for short review summarization
WI '17: Proceedings of the International Conference on Web IntelligenceWith the abundance of reviews published on the Web about a given product, consumers are looking for ways to view major opinions that can be presented in a quick and succinct way. Reviews contain many different opinions, making the ability to show a ...
Feature and Opinion Mining for Customer Review Summarization
PReMI '09: Proceedings of the 3rd International Conference on Pattern Recognition and Machine IntelligenceIn this paper, we present an opinion mining system to identify product features and opinions from review documents. The features and opinions are extracted using semantic and linguistic analysis of text documents. The polarity of opinion sentences is ...
Exploring the Incorporation of Opinion Polarity for Abstractive Multi-document Summarisation
Advances in Information RetrievalAbstractAbstractive multi-document summarisation (MDS) remains a challenging task. Part of the problem is the question as to how to preserve a document’s polarity in the summary. We propose an opinion polarity attention model for MDS, which incorporates a ...
Comments