{"type":"ScholarlyArticle","title":"A Structured Latent Variable Recurrent Network With Stochastic Attention For Generating Weibo Comments","authors":[{"name":"Shijie Yang","slug":"shijie-yang","given":"Shijie","family":"Yang","affiliation":"University of Chinese Academy of Sciences , China"},{"name":"Liang Li","slug":"liang-li","given":"Liang","family":"Li","affiliation":"Key Lab of Intell. Info. Process. , Inst. of Comput. Tech. , Chinese Academy of Sciences , China"},{"name":"Shuhui Wang","slug":"shuhui-wang","given":"Shuhui","family":"Wang","affiliation":"Key Lab of Intell. Info. Process. , Inst. of Comput. Tech. , Chinese Academy of Sciences , China"},{"name":"Weigang Zhang","slug":"weigang-zhang","given":"Weigang","family":"Zhang","affiliation":"School of Computer Science and Technology , Harbin Institute of Technology , China"},{"name":"Qingming Huang","slug":"qingming-huang","given":"Qingming","family":"Huang","affiliation":"University of Chinese Academy of Sciences , China; Key Lab of Intell. Info. Process. , Inst. of Comput. Tech. , Chinese Academy of Sciences , China; Peng Cheng Laboratory , China"},{"name":"Qi Tian","slug":"qi-tian","given":"Qi","family":"Tian","affiliation":"Noah's Ark Lab , Huawei Technologies , China"}],"abstract":"Building intelligent agents to generate realistic Weibo comments is challenging. For such realistic Weibo comments, the key criterion is improving diversity while maintaining coherency. Considering that the variability of linguistic comments arises from multi-level sources, including both discourse-level properties and word-level selections, we improve the comment diversity by leveraging such inherent hierarchy. In this paper, we propose a structured latent variable recurrent network, which exploits the hierarchical-structured latent variables with stochastic attention to model the variations of comments. First, we endow both discourse-level and word-level latent variables with hierarchical and temporal dependencies for constructing multi-level hierarchy. Second, we introduce a stochastic attention to infer the key-words of interest in the input post. As a result, diverse comments can be generated with both discourse-level properties and local-word selections. Experiments on open-domain Weibo data show that our model generates more diverse and realistic comments.","doi":"10.24963/ijcai.2020/548","url":"https://ijcai.org/proceedings/2020/548","pdf":"https://ijcai.org/proceedings/2020/0548.pdf","markdown":"https://ijcai.org/proceedings/2020/548.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/548","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Natural Language Processing","track":"Main track","number":548,"pages":{"first":3962,"last":3968},"keywords":["Natural Language Processing: NLP Applications and Tools","Natural Language Processing: Natural Language Generation","Machine Learning: Deep Generative Models"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/25381/file_25381.m3u8","length_sec":190,"provider":"hls"}],"references":[{"position":1,"raw":"[Bowman et al., 2015] Samuel R Bowman, Luke Vilnis, Oriol Vinyals, Andrew M Dai, Rafal Jozefowicz, and Samy Bengio. Generating sentences from a continuous space. Computer Science, 2015.","title":"Generating sentences from a continuous space","authors":"Luke Samuel R Bowman, Oriol Vilnis, Andrew M Vinyals, Rafal Dai, Samy Jozefowicz, Bengio","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cao and Clark, 2017] Kris Cao and Stephen Clark. Latent variable dialogue models and their diversity. In Confer- ence of the European Chapter of the Association for Com- putational Linguistics, pages 182-187, 2017.","title":"Latent variable dialogue models and their diversity","authors":"Clark ; Cao, Kris Cao, Stephen Clark","year":"2017","venue":"Conference of the European Chapter of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chung et al., 2015] Junyoung Chung, Kyle Kastner, Lau- rent Dinh, Kratarth Goel, Aaron Courville, and Yoshua Bengio. A recurrent latent variable model for sequential data. Computer Science, 35(8):1340-1353, 2015.","title":"A recurrent latent variable model for sequential data","authors":"Chung","year":"2015","venue":"Computer Science","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Eric and Manning, 2017] Mihail Eric and Christopher D Manning. Key-value retrieval networks for task-oriented dialogue. arXiv preprint arXiv:1705.05414, 2017.","title":"Key-value retrieval networks for task-oriented dialogue","authors":"Mihail Eric, Christopher D Manning","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gao et al., 2019] Xiang Gao, Sungjin Lee, Yizhe Zhang, Chris Brockett, Michel Galley, Jianfeng Gao, and Bill Dolan. Jointly optimizing diversity and relevance in neural response generation. NAACL, 2019.","title":"Jointly optimizing diversity and relevance in neural response generation","authors":"Xiang Gao, Sungjin Lee, Yizhe Zhang, Chris Brockett, Michel Galley, Jianfeng Gao, Bill Dolan","year":"2019","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Goddeau et al., 1996] D Goddeau, H Meng, J Polifroni, and S Seneff. A form-based dialogue manager for spoken lan- guage applications. In International Conference on Spoken Language, 1996, pages 701-704 vol.2, 1996.","title":"A form-based dialogue manager for spoken language applications","authors":"H Goddeau, J Meng, Polifroni, Seneff","year":"1996","venue":"International Conference on Spoken Language","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Holtzman et al., 2019] Ari Holtzman, Jan Buys, Maxwell Forbes, and Yejin Choi. The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751, 2019.","title":"The curious case of neural text degeneration","authors":"Holtzman","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Jieba, 2018] Jieba. https://pypi.org/project/jieba/. 2018.","title":null,"authors":"Jieba","year":"2018","venue":null,"doi":null,"url":"https://pypi.org/project/jieba/.2018","internal_url":null},{"position":9,"raw":"[Kingma and Welling, 2013] Diederik P Kingma and Max Welling. Auto-encoding variational bayes. arXiv, 2013.","title":"Auto-encoding variational bayes","authors":"P Diederik, Max Kingma, Welling","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Li et al., 2016] Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. A diversity-promoting ob- jective function for neural conversation models. Computer Science, 2016.","title":"A diversity-promoting objective function for neural conversation models","authors":"Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, Bill Dolan","year":"2016","venue":"Computer Science","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liu et al., 2018] Daqing Liu, Zheng-Jun Zha, Hanwang Zhang, Yongdong Zhang, and Feng Wu. Context-aware visual policy network for sequence-level image caption- ing. ACM MM, 2018.","title":"Context-aware visual policy network for sequence-level image captioning","authors":"Daqing Liu, Zheng-Jun Zha, Hanwang Zhang, Yongdong Zhang, Feng Wu","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liu et al., 2019] Xuejing Liu, Liang Li, Shuhui Wang, Zheng-Jun Zha, Dechao Meng, and Qingming Huang. Adaptive reconstruction network for weakly supervised re- ferring expression grounding. IEEE ICCV, 2019.","title":"Adaptive reconstruction network for weakly supervised referring expression grounding","authors":"Xuejing Liu, Liang Li, Shuhui Wang, Zheng-Jun Zha, Dechao Meng, Qingming Huang","year":"2019","venue":"IEEE ICCV","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Mou et al., 2016] Lili Mou, Yiping Song, Rui Yan, Ge Li, Lu Zhang, and Zhi Jin. Sequence to backward and forward sequences: A content-introducing approach to generative short-text conversation. arXiv preprint arXiv:1607.00970, 2016.","title":"Sequence to backward and forward sequences: A content-introducing approach to generative short-text conversation","authors":"Lili Mou, Yiping Song, Rui Yan, Ge Li, Lu Zhang, Zhi Jin","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Park et al., 2018] Yookoon Park, Jaemin Cho, and Gunhee Kim. A hierarchical latent structure for variational conver- sation modeling. NAACL, 2018.","title":"A hierarchical latent structure for variational conversation modeling","authors":"Park","year":"2018","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Serban et al., 2017] Iulian Vlad Serban, Alessandro Sor- doni, Ryan Lowe, Laurent Charlin, Joelle Pineau, Aaron C Courville, and Yoshua Bengio. A hierarchical latent vari- able encoder-decoder model for generating dialogues. In AAAI, pages 3295-3301, 2017.","title":"A hierarchical latent variable encoder-decoder model for generating dialogues","authors":"Iulian Vlad Serban, Alessandro Sordoni, Ryan Lowe, Laurent Charlin, Joelle Pineau, Aaron C Courville, Yoshua Bengio","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Shao et al., 2017] Louis Shao, Stephan Gouws, Denny Britz, Anna Goldie, Brian Strope, and Ray Kurzweil. Gen- erating long and diverse responses with neural conversa- tion models. arXiv preprint arXiv:1701.03185, 2017.","title":"Generating long and diverse responses with neural conversation models","authors":"Shao","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Shen et al., 2017] Xiaoyu Shen, Hui Su, Yanran Li, Wen- jie Li, Shuzi Niu, Yang Zhao, Akiko Aizawa, and Guop- ing Long. A conditional variational framework for dialog generation. arXiv preprint arXiv:1705.00316, 2017.","title":"A conditional variational framework for dialog generation","authors":"Xiaoyu Shen, Hui Su, Yanran Li, Wenjie Li, Shuzi Niu, Yang Zhao, Akiko Aizawa, Guoping Long","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Shen et al., 2019] Dinghan Shen, Asli Celikyilmaz, Yizhe Zhang, Liqun Chen, Xin Wang, Jianfeng Gao, and Lawrence Carin. Towards generating long and coherent text with multi-level latent variable models. ACL, 2019.","title":"Towards generating long and coherent text with multi-level latent variable models","authors":"Shen","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Sutskever et al., 2014] Ilya Sutskever, Oriol Vinyals, and Quoc V Le. Sequence to sequence learning with neural networks. 4:3104-3112, 2014.","title":"Ilya Sutskever, Oriol Vinyals, and Quoc V Le. Sequence to sequence learning with neural networks","authors":"Sutskever","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Vijayakumar et al., 2016] Ashwin K Vijayakumar, Michael Cogswell, Ramprasath R Selvaraju, Qing Sun, Stefan Lee, David Crandall, and Dhruv Batra. Diverse beam search: Decoding diverse solutions from neural sequence models. arXiv preprint arXiv:1610.02424, 2016.","title":"Diverse beam search: Decoding diverse solutions from neural sequence models","authors":"K Ashwin, Michael Vijayakumar, Cogswell, Qing Ramprasath R Selvaraju, Stefan Sun, David Lee, Dhruv Crandall, Batra","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"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, volume 17, 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":22,"raw":"[Yang et al., 2019] Tianhao Yang, Zheng-Jun Zha, and Han- wang Zhang. Making history matter: History-advantage sequence training for visual dialog. IEEE ICCV, 2019.","title":"Making history matter: History-advantage sequence training for visual dialog","authors":"Tianhao Yang, Zheng-Jun Zha, Hanwang Zhang","year":"2019","venue":"IEEE ICCV","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yao et al., 2016] Kaisheng Yao, Baolin Peng, Geoffrey Zweig, and Kam-Fai Wong. An attentional neural con- versation model with improved specificity. arXiv preprint arXiv:1606.01292, 2016.","title":"An attentional neural conversation model with improved specificity","authors":"Yao","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zha et al., 2019] Zheng-Jun Zha, Daqing Liu, Hanwang Zhang, Yongdong Zhang, and Feng Wu. Context-aware visual policy network for fine-grained image captioning. IEEE Trans. on PAMI, 2019.","title":"Context-aware visual policy network for fine-grained image captioning","authors":"Zheng-Jun Zha, Daqing Liu, Hanwang Zhang, Yongdong Zhang, Feng Wu","year":"2019","venue":"IEEE Trans. on PAMI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhang et al., 2018] Yizhe Zhang, Michel Galley, Jianfeng Gao, Zhe Gan, Xiujun Li, Chris Brockett, and Bill Dolan. Generating informative and diverse conversational re- sponses via adversarial information maximization. In Ad- vances in Neural Information Processing Systems, pages 1810-1820, 2018.","title":"Generating informative and diverse conversational responses via adversarial information maximization","authors":"Zhang","year":"2018","venue":"Advances in Neural Information Processing Systems","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 dialog models using conditional variational autoencoders. arXiv, pages 654-664, 2017.","title":"Learning discourse-level diversity for neural dialog models using conditional variational autoencoders","authors":"Zhao","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhou et al., 2017a] Ganbin Zhou, Ping Luo, Rongyu Cao, Fen Lin, Bo Chen, and Qing He. Mechanism-aware neu- ral machine for dialogue response generation. In AAAI Conference on Artificial Intelligence, AAAI, 2017.","title":"Mechanism-aware neural machine for dialogue response generation","authors":"Zhou","year":"2017","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhou et al., 2017b] Hao Zhou, Minlie Huang, Tianyang Zhang, Xiaoyan Zhu, and Bing Liu. Emotional chatting machine: emotional conversation generation with internal and external memory. arXiv preprint arXiv:1704.01074, 2017.","title":"Emotional chatting machine: emotional conversation generation with internal and external memory","authors":"Zhou","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}