{"type":"ScholarlyArticle","title":"Sentiment-Controllable Chinese Poetry Generation","authors":[{"name":"Huimin Chen","slug":"huimin-chen","given":"Huimin","family":"Chen","affiliation":"Department of Computer Science and Technology , Tsinghua University; Institute for Artificial Intelligence , Tsinghua University; Beijing National Research Center for Information Science and Technology , Tsinghua University; State Key Lab on Intelligent Technology and Systems , Tsinghua University {chm15 , yi-xy16 ,"},{"name":"Xiaoyuan Yi","slug":"xiaoyuan-yi","given":"Xiaoyuan","family":"Yi","affiliation":"Department of Computer Science and Technology , Tsinghua University; Institute for Artificial Intelligence , Tsinghua University; Beijing National Research Center for Information Science and Technology , Tsinghua University; State Key Lab on Intelligent Technology and Systems , Tsinghua University {chm15 , yi-xy16 ,"},{"name":"Maosong Sun","slug":"maosong-sun","given":"Maosong","family":"Sun","affiliation":"Department of Computer Science and Technology , Tsinghua University; Institute for Artificial Intelligence , Tsinghua University; Beijing National Research Center for Information Science and Technology , Tsinghua University; State Key Lab on Intelligent Technology and Systems , Tsinghua University {chm15 , yi-xy16 ,"},{"name":"Wenhao Li","slug":"wenhao-li","given":"Wenhao","family":"Li","affiliation":"Department of Computer Science and Technology , Tsinghua University; Institute for Artificial Intelligence , Tsinghua University; Beijing National Research Center for Information Science and Technology , Tsinghua University; State Key Lab on Intelligent Technology and Systems , Tsinghua University {chm15 , yi-xy16 ,"},{"name":"Cheng Yang","slug":"cheng-yang","given":"Cheng","family":"Yang","affiliation":"Department of Computer Science and Technology , Tsinghua University; Institute for Artificial Intelligence , Tsinghua University; Beijing National Research Center for Information Science and Technology , Tsinghua University; State Key Lab on Intelligent Technology and Systems , Tsinghua University {chm15 , yi-xy16 ,"},{"name":"Zhipeng Guo","slug":"zhipeng-guo","given":"Zhipeng","family":"Guo","affiliation":"Department of Computer Science and Technology , Tsinghua University; Institute for Artificial Intelligence , Tsinghua University; Beijing National Research Center for Information Science and Technology , Tsinghua University; State Key Lab on Intelligent Technology and Systems , Tsinghua University {chm15 , yi-xy16 ,"}],"abstract":"Expressing diverse sentiments is one of the main purposes of human poetry creation. Existing Chinese poetry generation models have made great progress in poetry quality, but they all neglected to endow generated poems with specific sentiments. Such defect leads to strong sentiment collapse or bias and thus hurts the diversity and semantics of generated poems. Meanwhile, there are few sentimental Chinese poetry resources for studying. To address this problem, we first collect a manually-labelled sentimental poetry corpus with fine-grained sentiment labels. Then we propose a novel semi-supervised conditional Variational Auto-Encoder model for sentiment-controllable poetry generation. Besides, since poetry is discourse-level text where the polarity and intensity of sentiment could transfer among lines, we incorporate a temporal module to capture sentiment transition patterns among different lines. Experimental results show our model can control the sentiment of not only a whole poem but also each line, and improve the poetry diversity against the state-of-the-art models without losing quality.","doi":"10.24963/ijcai.2019/684","url":"https://ijcai.org/proceedings/2019/684","pdf":"https://ijcai.org/proceedings/2019/0684.pdf","markdown":"https://ijcai.org/proceedings/2019/684.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/684","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Natural Language Processing","track":"Main track","number":684,"pages":{"first":4925,"last":4931},"keywords":["Natural Language Processing: Natural Language Processing","Natural Language Processing: Natural Language Generation"],"videos":[],"references":[{"position":1,"raw":"[Bahdanau et al., 2015] Dzmitry Bahdanau, KyungHyun Cho, and Yoshua Bengio. Neural machine translation by jointly learning to align and translate. In Proceedings of the 2015 ICLR, San Diego, CA, 2015.","title":"Neural machine translation by jointly learning to align and translate","authors":"Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio","year":"2015","venue":"Proceedings of the 2015 ICLR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cagan et al., 2017] Tomer Cagan, Stefan L Frank, and Reut Tsarfaty. Data-driven broad-coverage grammars for opin- ionated natural language generation (onlg). 2017.","title":"Data-driven broad-coverage grammars for opinionated natural language generation","authors":"Stefan L Tomer Cagan, Reut Frank, Tsarfaty","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chari, 1976] VK Chari. Poetic emotions and poetic se- mantics. The Journal of Aesthetics and Art Criticism, 34(3):287-299, 1976.","title":"Poetic emotions and poetic semantics","authors":"Vk Chari","year":"1976","venue":"The Journal of Aesthetics and Art Criticism","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. In Proceedings of the 2014 EMNLP, pages 1724-1734, Doha, Qatar, 2014.","title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":"Proceedings of the 2014 EMNLP","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gervás, 2001] Pablo Gervás. An Expert System for the Composition of Formal Spanish Poetry, pages 181-188. Springer London, 2001.","title":"Pablo Gervás. An Expert System for the Composition of Formal Spanish Poetry","authors":"Gervás","year":"2001","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Ghazvininejad et al., 2016] Marjan Ghazvininejad, Xing Shi, Yejin Choi, and Kevin Knight. Generating topical poetry. In Proceedings of the 2016 EMNLP, pages 1183- 1191, Texas, USA, 2016.","title":"Generating topical poetry","authors":"Marjan Ghazvininejad, Xing Shi, Yejin Choi, Kevin Knight","year":"2016","venue":"Proceedings of the 2016 EMNLP","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[He et al., 2012] Jing He, Ming Zhou, and Long Jiang. Gen- erating chinese classical poems with statistical machine translation models. In Proceedings of the 2012 AAAI, pages 1650-1656, Toronto, Canada, 2012.","title":"Generating chinese classical poems with statistical machine translation models","authors":"Jing He, Ming Zhou, Long Jiang","year":"2012","venue":"Proceedings of the 2012 AAAI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hu et al., 2017] Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P Xing. Toward controlled generation of text. In Proceedings of the 2017 ICML, pages 1587-1596. JMLR. org, 2017.","title":"Toward controlled generation of text","authors":"Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, Eric P Xing","year":"2017","venue":"Proceedings of the 2017 ICML","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Janowitz, 1973] KE Janowitz. The antipodes of self: Three poems by christina rossetti. Victorian Poetry, pages 195- 205, 1973.","title":"The antipodes of self: Three poems by christina rossetti","authors":"; Ke Janowitz, Janowitz","year":"1973","venue":"Victorian Poetry","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kingma and Ba, 2015] Diederik P. Kingma and Jimmy Lei Ba. Adam: A method for stochastic optimization. In Pro- ceedings of the 2015 International Conference on Learn- ing Representations, San Diego, CA, 2015.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Lei Kingma, Ba","year":"2015","venue":"Proceedings of the 2015 International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kingma et al., 2014] Diederik P. Kingma, Danilo J. Rezende, Shakir Mohamed, and Max Welling. Semi- supervised learning with deep generative models. In In Advances in 2014 NeurlPS, Montreal, Canada, 2014.","title":"Semisupervised learning with deep generative models","authors":"P Diederik, Danilo J Kingma, Shakir Rezende, Max Mohamed, Welling","year":"2014","venue":"Advances in 2014 NeurlPS","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Levy, 2001] Robert P. Levy. A computational model of po- etic creativity with neural network as measure of adaptive fitness. In Proceedings of the ICCBR-01 Workshop on Cre- ative Systems, 2001.","title":"A computational model of poetic creativity with neural network as measure of adaptive fitness","authors":"Robert P Levy","year":"2001","venue":"Proceedings of the ICCBR-01 Workshop on Creative Systems","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Manurung, 2003] Hisar Maruli Manurung. An evolutionary algorithm approach to poetry generation. PhD thesis, Uni- versity of Edinburgh, 2003.","title":"An evolutionary algorithm approach to poetry generation","authors":"Hisar Maruli, Manurung","year":"2003","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Mihalcea and Tarau, 2004] Rada Mihalcea and Paul Tarau. Textrank: Bringing order into text. In Proceedings of the 2004 EMNLP, 2004.","title":"Textrank: Bringing order into text","authors":"Tarau Mihalcea, Rada Mihalcea, Paul Tarau","year":"2004","venue":"Proceedings of the 2004 EMNLP","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Morris-Jones, 1962] Huw Morris-Jones. The language of feelings. The British Journal of Aesthetics, 2(1):17-25, 1962.","title":"Huw Morris-Jones. The language of feelings","authors":"Morris-Jones","year":"1962","venue":"The British Journal of Aesthetics","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Wang and Wan, 2018] Ke Wang and Xiaojun Wan. Senti- gan: Generating sentimental texts via mixture adversarial networks. In Proceedings of the 2018 IJCAI, pages 4446- 4452, 2018.","title":"Sentigan: Generating sentimental texts via mixture adversarial networks","authors":"Wang, Wan ; ] Ke Wang, Xiaojun Wan","year":"2018","venue":"Proceedings of the 2018 IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/618"},{"position":17,"raw":"[Wang et al., 2016a] Qixin Wang, Tianyi Luo, Dong Wang, and Chao Xing. Chinese song iambics generation with neural attention-based model. In Proceedings of the 2016 IJCAI, pages 2943-2949, New York, USA, 2016.","title":"Chinese song iambics generation with neural attention-based model","authors":"Wang","year":"2016","venue":"Proceedings of the 2016 IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/418"},{"position":18,"raw":"[Wang et al., 2016b] Zhe Wang, Wei He, Hua Wu nad Haiyang Wu, Wei Li, Haifeng Wang, and Enhong Chen. Chinese poetry generation with planning based neural net- work. In Proceedings of COLING 2016, pages 1051-1060, Osaka, Japan, 2016.","title":"Chinese poetry generation with planning based neural network","authors":"Wang","year":"2016","venue":"Proceedings of COLING 2016","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Wei et al., 2018] Jia Wei, Qiang Zhou, and Yici Cai. Poet- based poetry generation: Controlling personal style with recurrent neural networks. In Proceedings of the Workshop on Computing, Networking and Communications, pages 156-160, 2018.","title":"Poetbased poetry generation: Controlling personal style with recurrent neural networks","authors":"Jia Wei, Qiang Zhou, Yici Cai","year":"2018","venue":"Proceedings of the Workshop on Computing, Networking and Communications","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Yang et al., 2018a] Cheng Yang, Maosong Sun, Xiaoyuan Yi, and Wenhao Li. Stylistic chinese poetry generation via unsupervised style disentanglement. In Proceedings of the 2018 EMNLP, pages 3960-3969, Brussels, Belgium, 2018.","title":"Stylistic chinese poetry generation via unsupervised style disentanglement","authors":"Yang","year":"2018","venue":"Proceedings of the 2018 EMNLP","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Yang et al., 2018b] Xiaopeng Yang, Xiaowen Lin, Shunda Suo, and Ming Li. Generating thematic chinese poetry using conditional variational autoencoders with hybrid de- coders. In Proceedings of the 2018 IJCAI, pages 4539- 4545, Stockholm, Sweden, 2018.","title":"Generating thematic chinese poetry using conditional variational autoencoders with hybrid decoders","authors":"Yang","year":"2018","venue":"Proceedings of the 2018 IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/631"},{"position":22,"raw":"[Yi et al., 2018a] Xiaoyuan Yi, Maosong Sun, Ruoyu Li, and Wenhao Li. Automatic poetry generation with mutual re- inforcement learning. In Proceedings of the 2018 EMNLP, pages 3143-3153, Brussels, Belgium, 2018.","title":"Automatic poetry generation with mutual reinforcement learning","authors":"Yi","year":"2018","venue":"Proceedings of the 2018 EMNLP","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yi et al., 2018b] Xiaoyuan Yi, Maosong Sun, Ruoyu Li, and Zonghan Yang. Chinese poetry generation with a working memory mode. In Proceedings of the 2018 IJCAI, pages 4553-4559, Stockholm, Sweden, 2018.","title":"Chinese poetry generation with a working memory mode","authors":"Yi","year":"2018","venue":"Proceedings of the 2018 IJCAI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zhang and Lapata, 2014] Xingxing Zhang and Mirella Lap- ata. Chinese poetry generation with recurrent neural net- works. In Proceedings of the 2014 EMNLP, pages 670- 680, Doha, Qatar, 2014.","title":"Chinese poetry generation with recurrent neural networks","authors":"Lapata ; Zhang, Mirella Zhang, Lapata","year":"2014","venue":"Proceedings of the 2014 EMNLP","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhang et al., 2017] Jiyuan Zhang, Yang Feng, Dong Wang, Yang Wang, Andrew Abel, Shiyue Zhang, and Andi Zhang. Flexible and creative chinese poetry generation using neural memory. In Proceedings of the 2017 ACL, pages 1364-1373. Association for Computational Linguis- tics, 2017.","title":"Flexible and creative chinese poetry generation using neural memory","authors":"Jiyuan Zhang, Yang Feng, Dong Wang, Yang Wang, Andrew Abel, Shiyue Zhang, Andi Zhang","year":"2017","venue":"Proceedings of the 2017 ACL","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhao et al., 2017] Tiancheng Zhao, Ran Zhao, and Maxine Eskenazi. Learning discourse-level diversity for neural di- alog models using conditional variational autoencoders. In Proceedings of the 2017 ACL, pages 654-664. Association for Computational Linguistics, 2017.","title":"Learning discourse-level diversity for neural dialog models using conditional variational autoencoders","authors":"Zhao","year":"2017","venue":"Proceedings of the 2017 ACL","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}