{"type":"ScholarlyArticle","title":"A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization","authors":[{"name":"Li Wang","slug":"li-wang","given":"Li","family":"Wang","affiliation":"Tencent Data Center of SNG"},{"name":"Junlin Yao","slug":"junlin-yao","given":"Junlin","family":"Yao","affiliation":"ETH Zürich"},{"name":"Yunzhe Tao","slug":"yunzhe-tao","given":"Yunzhe","family":"Tao","affiliation":"Columbia University"},{"name":"Li Zhong","slug":"li-zhong","given":"Li","family":"Zhong","affiliation":"Tencent Data Center of SNG"},{"name":"Wei Liu","slug":"wei-liu","given":"Wei","family":"Liu","affiliation":"Tencent AI Lab"},{"name":"Qiang Du","slug":"qiang-du","given":"Qiang","family":"Du","affiliation":"Columbia University"}],"abstract":"In this paper, we propose a deep learning approach to tackle the automatic summarization tasks by incorporating topic information into the convolutional sequence-to-sequence (ConvS2S) model and using self-critical sequence training (SCST) for optimization. Through jointly attending to topics and word-level alignment, our approach can improve coherence, diversity, and informativeness of generated summaries via a biased probability generation mechanism. On the other hand, reinforcement training, like SCST, directly optimizes the proposed model with respect to the non-differentiable metric ROUGE, which also avoids the exposure bias during inference. We carry out the experimental evaluation with state-of-the-art methods over the Gigaword, DUC-2004, and LCSTS datasets. The empirical results demonstrate the superiority of our proposed method in the abstractive summarization.","doi":"10.24963/ijcai.2018/619","url":"https://ijcai.org/proceedings/2018/619","pdf":"https://ijcai.org/proceedings/2018/0619.pdf","markdown":"https://ijcai.org/proceedings/2018/619.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/619","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Natural Language Processing","track":"Main track","number":619,"pages":{"first":4453,"last":4460},"keywords":["Machine Learning Applications: Applications of Reinforcement Learning","Machine Learning: Neural Networks","Machine Learning: Deep Learning","Natural Language Processing: Natural Language Summarization"],"videos":[],"references":[{"position":1,"raw":"[Bahdanau et al., 2014] Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473, 2014.","title":"Neural machine translation by jointly learning to align and translate","authors":"Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Barzilay and McKeown, 2005] Regina Barzilay and Kath- leen R McKeown. Sentence fusion for multidocu- ment news summarization. Computational Linguistics, 31(3):297-328, 2005.","title":"Sentence fusion for multidocument news summarization","authors":"Mckeown Barzilay, Regina Barzilay, Kathleen R Mckeown","year":"2005","venue":"Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Blei et al., 2003] David M Blei, Andrew Y Ng, and Michael I Jordan. Latent dirichlet allocation. Journal of machine Learning research, 3(Jan):993-1022, 2003.","title":"Latent dirichlet allocation","authors":"Andrew Y David M Blei, Michael I Ng, Jordan","year":"2003","venue":"Journal of machine Learning research","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078, 2014.","title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chopra et al., 2016] Sumit Chopra, Michael Auli, and Alexander M Rush. Abstractive sentence summarization with attentive recurrent neural networks. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 93-98, 2016.","title":"Abstractive sentence summarization with attentive recurrent neural networks","authors":"Sumit Chopra, Michael Auli, Alexander M Rush","year":"2016","venue":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dauphin et al., 2016] Yann N Dauphin, Angela Fan, Michael Auli, and David Grangier. Language modeling with gated convolutional networks. arXiv preprint arXiv:1612.08083, 2016.","title":"Language modeling with gated convolutional networks","authors":"Angela Yann N Dauphin, Michael Fan, David Auli, Grangier","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gehring et al., 2017] Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, and Yann N Dauphin. Convo- lutional sequence to sequence learning. arXiv preprint arXiv:1705.03122, 2017.","title":"Convolutional sequence to sequence learning","authors":"Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann N Dauphin","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Graff and Cieri, 2003] David Graff and C Cieri. English gi- gaword corpus. Linguistic Data Consortium, 2003.","title":"English gigaword corpus","authors":"David Graff, C Cieri","year":"2003","venue":"Linguistic Data Consortium","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gu et al., 2016] Jiatao Gu, Zhengdong Lu, Hang Li, and Victor OK Li. Incorporating copying mecha- nism in sequence-to-sequence learning. arXiv preprint arXiv:1603.06393, 2016.","title":"Incorporating copying mechanism in sequence-to-sequence learning","authors":"Gu","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"Schmidhuber Hochreiter, Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hu et al., 2015] Baotian Hu, Qingcai Chen, and Fangze Zhu. Lcsts: A large scale chinese short text summariza- tion dataset. arXiv preprint arXiv:1506.05865, 2015.","title":"Lcsts: A large scale chinese short text summarization dataset","authors":"Hu","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kraaij et al., 2002] Wessel Kraaij, Martijn Spitters, and Anette Hulth. Headline extraction based on a combina- tion of uni-and multidocument summarization techniques. In Proceedings of the ACL workshop on Automatic Sum- marization/Document Understanding Conference (DUC 2002). ACL, 2002.","title":"Headline extraction based on a combination of uni-and multidocument summarization techniques","authors":"Martijn Wessel Kraaij, Anette Spitters, Hulth","year":"2002","venue":"Proceedings of the ACL workshop on Automatic Summarization/Document Understanding Conference (DUC 2002). ACL","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lin, 2004] Chin-Yew Lin. Rouge: A package for auto- matic evaluation of summaries. In Text summarization branches out: Proceedings of the ACL-04 workshop, vol- ume 8. Barcelona, Spain, 2004.","title":"Rouge: A package for automatic evaluation of summaries","authors":"Chin-Yew Lin","year":"2004","venue":"Text summarization branches out: Proceedings of the ACL-04 workshop","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Nallapati et al., 2016a] Ramesh Nallapati, Bing Xiang, and Bowen Zhou. Sequence-to-sequence rnns for text summa- rization. 2016.","title":"Sequence-to-sequence rnns for text summarization","authors":"Nallapati","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Nallapati et al., 2016b] Ramesh Nallapati, Bowen Zhou, Caglar Gulcehre, Bing Xiang, et al. Abstractive text sum- marization using sequence-to-sequence rnns and beyond. arXiv preprint arXiv:1602.06023, 2016.","title":"Abstractive text summarization using sequence-to-sequence rnns and beyond","authors":"Nallapati","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Neto et al., 2002] Joel Neto, Alex Freitas, and Celso Kaest- ner. Automatic text summarization using a machine learn- ing approach. Advances in Artificial Intelligence, pages 205-215, 2002.","title":"Automatic text summarization using a machine learning approach","authors":"Joel Neto, Alex Freitas, Celso Kaestner","year":"2002","venue":"Advances in Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Over et al., 2007] Paul Over, Hoa Dang, and Donna Har- man. Duc in context. Information Processing & Man- agement, 43(6):1506-1520, 2007.","title":"Duc in context","authors":"Paul Over, Hoa Dang, Donna Harman","year":"2007","venue":"Information Processing & Management","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Paszke et al., 2017] Adam Paszke, Sam Gross, and Soumith Chintala. Pytorch, 2017.","title":"Pytorch","authors":"Adam Paszke, Sam Gross, Soumith Chintala","year":"2017","venue":"Pytorch","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Paulus et al., 2017] Romain Paulus, Caiming Xiong, and Richard Socher. A deep reinforced model for abstractive summarization. CoRR, abs/1705.04304, 2017.","title":"A deep reinforced model for abstractive summarization","authors":"Romain Paulus, Caiming Xiong, Richard Socher","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ranzato et al., 2015] Marc'Aurelio Ranzato, Sumit Chopra, Michael Auli, and Wojciech Zaremba. Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732, 2015.","title":"Sequence level training with recurrent neural networks","authors":"Ranzato","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Rennie et al., 2016] Steven J Rennie, Etienne Marcheret, Youssef Mroueh, Jarret Ross, and Vaibhava Goel. Self- critical sequence training for image captioning. arXiv preprint arXiv:1612.00563, 2016.","title":"Selfcritical sequence training for image captioning","authors":"Etienne Steven J Rennie, Youssef Marcheret, Jarret Mroueh, Vaibhava Ross, Goel","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rush et al., 2015] Alexander M Rush, Sumit Chopra, and Jason Weston. A neural attention model for ab- stractive sentence summarization. arXiv preprint arXiv:1509.00685, 2015.","title":"A neural attention model for abstractive sentence summarization","authors":"Sumit Alexander M Rush, Jason Chopra, Weston","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Shen et al., 2016] Shiqi Shen, Yu Zhao, Zhiyuan Liu, Maosong Sun, et al. Neural headline genera- tion with sentence-wise optimization. arXiv preprint arXiv:1604.01904, 2016.","title":"Neural headline generation with sentence-wise optimization","authors":"Shiqi Shen, Yu Zhao, Zhiyuan Liu, Maosong Sun","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Sutskever et al., 2013] Ilya Sutskever, James Martens, George Dahl, and Geoffrey Hinton. On the importance of initialization and momentum in deep learning. In International conference on machine learning, pages 1139-1147, 2013.","title":"On the importance of initialization and momentum in deep learning","authors":"Sutskever","year":"2013","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Sutskever et al., 2014] Ilya Sutskever, Oriol Vinyals, and Quoc V Le. Sequence to sequence learning with neural networks. In Advances in neural information processing systems, pages 3104-3112, 2014.","title":"Quoc V Le. Sequence to sequence learning with neural networks","authors":"Sutskever","year":"2014","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Williams and Zipser, 1989] R. J. Williams and D. Zipser. A learning algorithm for continually running fully recurrent neural networks. Neural Computation, 1(2):270-280, June 1989.","title":"A learning algorithm for continually running fully recurrent neural networks","authors":"R J Williams, D Zipser","year":"1989","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Xing et al., 2017] Chen Xing, Wei Wu, Yu Wu, Jie Liu, Yalou Huang, Ming Zhou, and Wei-Ying Ma. Topic aware neural response generation. In AAAI, pages 3351-3357, 2017.","title":"Topic aware neural response generation","authors":"Chen Xing, Wei Wu, Yu Wu, Jie Liu, Yalou Huang, Ming Zhou, Wei-Ying Ma","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhou et al., 2017] Qingyu Zhou, Nan Yang, Furu Wei, and Ming Zhou. Selective encoding for abstractive sentence summarization. arXiv preprint arXiv:1704.07073, 2017.","title":"Selective encoding for abstractive sentence summarization","authors":"Qingyu Zhou, Nan Yang, Furu Wei, Ming Zhou","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}