Elamur Research⌕
☰
home / papers / 2019 / Target-Guided Open-Domain Conversation

Target-Guided Open-Domain Conversation

Paper · 2019 · Jianheng Tang, Tiancheng Zhao, Chenyan Xiong et al.

Summary

The paper asks how an open-domain chatbot can pursue a goal: talk naturally with a person while steering the dialogue toward a hidden target word, such as "e-books" or "McDonald's". This setting is relevant to recommendation, education and therapy. No public data exists for learning this behaviour end to end, so the authors split the task into two parts.

First, smoothness at each turn is learned with supervision from ordinary chit-chat. A module predicts keywords for the next reply, and these keywords then guide retrieval of the response. Second, progress toward the target comes from a simple rule at the discourse level: each new keyword must be closer to the target than the previous one.

To train the system, the authors added keywords to an existing everyday chat corpus (Zhang et al., 2018). They compared three ways of predicting keyword transitions: PMI-based, neural, and a hybrid kernel-based method. In simulation and in human tests, the Kernel agent reached targets more often and transitioned more smoothly than the baselines. The work is an early step toward connecting chit-chat with task-oriented dialogue.

Key points

  • The system has three modules: a turn-level keyword transition predictor, a discourse-level target-guiding strategy, and a keyword-augmented response retriever.
  • A target counts as reached once either speaker mentions it or a closely similar word.
  • Human evaluation used 50 test cases with at most 8 turns. Turkers judged whether the target was reached and rated smoothness from 1 to 5.
  • Adding the guiding strategy to a plain Retrieval agent (Retrieval-Stgy) kept smoothness about the same while raising the success rate considerably.
  • In side-by-side comparisons, the Kernel agent won 30–50% of pairings against other agents. Data and code are on GitHub (squareRoot3/Target-Guided-Conversation).

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Carnegie Mellon UniversityPittsburgh · United States365 works · 158,048 citations🏢MicrosoftRedmond · United States240 works · 123,537 citations🎓Sun Yat-sen UniversityGuangzhou · China23 works · 8,980 citations

📚 Shelves 4 Computer Science · 9,086 works Artificial Intelligence · 8,889 works Arts and Humanities · 9,296 works Language and Linguistics · 9,206 works

Cite

Cite as Jianheng Tang, Tiancheng Zhao, Chenyan Xiong, Xiaodan Liang, Eric Xing and Zhiting Hu. 2019. Target-Guided Open-Domain Conversation. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/p19-1565

@inproceedings{tang2019target,
  title = {{Target-Guided Open-Domain Conversation}},
  author = {Jianheng Tang, Tiancheng Zhao, Chenyan Xiong, Xiaodan Liang, Eric Xing and Zhiting Hu},
  booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  year = {2019},
  doi = {10.18653/v1/p19-1565},
  url = {https://doi.org/10.18653/v1/p19-1565}
}

References

44 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Kris Cao, Angeliki Lazaridou, Marc Lanctot, Joel Z Leibo, Karl Tuyls, and Stephen Clark. 2018. Emergent communication through negotiation. In ICLR. find
  2. Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555. find
  3. Kenneth Ward Church and Patrick Hanks. 1990. Word association norms, mutual information, and lexicography. Computational linguistics, 16(1):22–29. our card
  4. David DeVault, Johnathan Mell, and Jonathan Gratch. 2015. Toward natural turn-taking in a virtual human negotiation agent. In 2015 AAAI Spring Symposium Series. find
  5. Bhuwan Dhingra, Lihong Li, Xiujun Li, Jianfeng Gao, Yun-Nung Chen, Faisal Ahmed, and Li Deng. 2017. find
  6. Towards end-to-end reinforcement learning of dialogue agents for information access. In ACL. our card
  7. Hao Fang, Hao Cheng, Maarten Sap, Elizabeth Clark, Ari Holtzman, Yejin Choi, Noah A Smith, and Mari Ostendorf. 2018. Sounding board: A user-centric and content-driven social chatbot. In NAACL System Demonstrations. find
  8. He He, Anusha Balakrishnan, Mihail Eric, and Percy Liang. 2017. Learning symmetric collaborative dialogue agents with dynamic knowledge graph embeddings. In ACL. find
  9. Chia-Wei Liu, Ryan Lowe, Iulian V Serban, Michael Noseworthy, Laurent Charlin, and Joelle Pineau. 2016. How not to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation. arXiv preprint arXiv:1603.08023. our card
  10. Shuman Liu, Hongshen Chen, Zhaochun Ren, Yang Feng, Qun Liu, and Dawei Yin. 2018. Knowledge diffusion for neural dialogue generation. In ACL, volume 1, pages 1489–1498. find
  11. George Miller. 1998. WordNet: An electronic lexical database. MIT press. find
  12. He He, Derek Chen, Anusha Balakrishnan, and Percy Liang. 2018. Decoupling strategy and generation in negotiation dialogues. arXiv preprint arXiv:1808.09637. our card
  13. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In EMNLP. our card
  14. Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, et al. 2019. Texar: A modularized, versatile, and extensible toolkit for text generation. In ACL System Demonstrations. find
  15. Lianhui Qin, Michel Galley, Chris Brockett, Xiaodong Liu, Xiang Gao, Bill Dolan, Yejin Choi, and Jianfeng Gao. 2019. Conversing by reading: Contentful neural conversation with on-demand machine reading. In ACL. find
  16. Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P Xing. 2017. Toward controlled generation of text. In ICML. our card
  17. Ashwin Ram, Rohit Prasad, Chandra Khatri, Anu Venkatesh, Raefer Gabriel, Qing Liu, Jeff Nunn, Behnam Hedayatnia, Ming Cheng, Ashish Nagar, et al. 2018. Conversational AI: The science behind the Alexa prize. arXiv preprint arXiv:1801.03604. find
  18. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. find
  19. Kyusong Lee, Tiancheng Zhao, Alan W Black, and Maxine Eskenazi. 2018. DialCrowd: A toolkit for easy dialog system assessment. In SIGDAIL, pages 245–248. find
  20. Antoine Raux, Brian Langner, Dan Bohus, Alan W Black, and Maxine Eskenazi. 2005. Let’s go public! taking a spoken dialog system to the real world. In Ninth European conference on speech communication and technology. find
  21. Mike Lewis, Denis Yarats, Yann N Dauphin, Devi Parikh, and Dhruv Batra. 2017. Deal or no deal? end-to-end learning for negotiation dialogues. arXiv preprint arXiv:1706.05125. — [arXiv:1706.05125](https://arxiv.org/abs/1706.05125) find
  22. Iulian Vlad Serban, Alessandro Sordoni, Ryan Lowe, Laurent Charlin, Joelle Pineau, Aaron Courville, and Yoshua Bengio. 2016. A hierarchical latent variable encoder-decoder model for generating dialogues. arXiv preprint arXiv:1605.06069. our card
  23. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2015. A diversity-promoting objective function for neural conversation models. arXiv preprint arXiv:1510.03055. our card
  24. Lifeng Shang, Zhengdong Lu, and Hang Li. 2015. Neural responding machine for short-text conversation. arXiv preprint arXiv:1503.02364. our card
  25. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016a. A persona-based neural conversation model. arXiv preprint arXiv:1603.06155. our card
  26. Jiwei Li, Will Monroe, Alan Ritter, Michel Galley, Jianfeng Gao, and Dan Jurafsky. 2016b. Deep reinforcement learning for dialogue generation. arXiv preprint arXiv:1606.01541. our card
  27. Raymond Li, Samira Ebrahimi Kahou, Hannes Schulz, Vincent Michalski, Laurent Charlin, and Chris Pal. 2018. Towards deep conversational recommendations. In NeurIPS, pages 9748–9758. find
  28. Shuai Lin, Wentao Wang, Zichao Yang, Haoran Shi, Frank Xu, Xiaodan Liang, Eric Xing, and Zhiting Hu. 2019. Toward unsupervised text content manipulation. arXiv preprint arXiv:1901.09501. — [arXiv:1901.09501](https://arxiv.org/abs/1901.09501) find
  29. Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi Jaakkola. 2017. Style transfer from non-parallel text by cross-alignment. In NeurIPS. our card
  30. Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, and Bill Dolan. 2015. A neural network approach to context-sensitive generation of conversational responses. arXiv preprint arXiv:1506.06714. our card
  31. Joseph Weizenbaum et al. 1966. ELIZA—a computer program for the study of natural language communication between man and machine. Communications of the ACM, 9(1):36–45. find
  32. Jason D Williams, Kavosh Asadi, and Geoffrey Zweig. 2017. Hybrid code networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning. In ACL. find
  33. Hua Wu, Yi Liu, Ying Chen, Wayne Xin Zhao, Daxiang Dong, Dianhai Yu, Xiangyang Zhou, and Lu Li. 2018. Multi-turn response selection for chatbots with deep attention matching network. In ACL. our card
  34. Yu Wu, Wei Wu, Chen Xing, Ming Zhou, and Zhoujun Li. 2016. Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots. arXiv preprint arXiv:1612.01627. our card
  35. Chenyan Xiong, Zhuyun Dai, Jamie Callan, Zhiyuan Liu, and Russell Power. 2017. End-to-end neural ad-hoc ranking with kernel pooling. In SIGIR, pages 55–64. ACM. find
  36. Zichao Yang, Zhiting Hu, Chris Dyer, Eric P Xing, and Taylor Berg-Kirkpatrick. 2018. Unsupervised text style transfer using language models as discriminators. In NeurIPS. our card
  37. Denis Yarats and Mike Lewis. 2018. Hierarchical text generation and planning for strategic dialogue. In ICML. find
  38. Stephanie Young, Jost Schatzmann, Karl Weilhammer, and Hui Ye. 2007. The hidden information state approach to dialog management. In Acoustics, Speech and Signal Processing, 2007. find
  39. ICASSP 2007. IEEE International Conference on, volume 4, pages IV– 149. IEEE. find
  40. Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, and Jason Weston. 2018. Personalizing dialogue agents: I have a dog, do you have pets too? arXiv preprint arXiv:1801.07243. our card
  41. Tiancheng Zhao, Kaige Xie, and Maxine Eskenazi. 2019. Rethinking action spaces for reinforcement learning in end-to-end dialog agents with latent variable models. arXiv preprint arXiv:1902.08858. our card
  42. Tiancheng Zhao, Ran Zhao, and Maxine Eskenazi. 2017. Learning discourse-level diversity for neural dialog models using conditional variational autoencoders. In ACL. our card
  43. Li Zhou, Jianfeng Gao, Di Li, and Heung-Yeung Shum. 2018. The design and implementation of xiaoice, an empathetic social chatbot. arXiv preprint arXiv:1812.08989. find
  44. Xiangyang Zhou, Daxiang Dong, Hua Wu, Shiqi Zhao, Dianhai Yu, Hao Tian, Xuan Liu, and Rui Yan. 2016. Multi-view response selection for human-computer conversation. In EMNLP. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tang-2019-target-guided-open-domain-conversation/