Elamur Research⌕
☰
home / papers / 2019 / Proactive Human-Machine Conversation with Explicit Conversation Goal

Proactive Human-Machine Conversation with Explicit Conversation Goal

Paper · 2019 · Wenquan Wu, Zhen Guo, Xiangyang Zhou et al.

Summary

Most dialogue systems simply react to the user and do not steer the exchange. This Baidu paper defines a task in which an agent must actively guide a chat toward a preset target: a two-hop path "[start] → topic a → topic b", where each topic is an entity in a knowledge graph. The authors crawled movie and film-star data from MTime.com. They built a graph that combines factual triplets with non-factoid objects such as comments and synopses. It also contains derived "associated" triplets, which link two entities that share a predicate–object pair. Crowdworkers then created DuConv, a Chinese dialogue corpus. In each dialogue, a leader who sees the goal and the related knowledge drives the topic shifts, and a follower replies without knowing the goal. The baselines are a knowledge-aware retrieval system, a knowledge-aware generator that learns prior/posterior distributions over knowledge, and a plain Seq2Seq model. Models that use knowledge outperformed those that do not. The generator used more facts while reaching the goal, which produced more diverse conversations. The released data and code serve as a benchmark for proactive, knowledge-grounded dialogue.

Key points

  • DuConv contains 29,858 dialogues and 270,399 utterances. Dialogues average 9.1 utterances, utterances average 10.6 words, and each dialogue comes with about 17.1 knowledge items.
  • The knowledge graph has 143,627 entities (91,874 movies and 51,753 people), 45 properties, and about 3.6M SPO triplets. A manual check of 100 sampled triplets found over 97% accuracy.
  • In human evaluation, the knowledge-aware generator outperformed both Seq2Seq and retrieval on informativeness, proactivity, goal completion and coherence. The retrieval model scored clearly lowest.
  • Replacing the goal entities with normalized "topic a"/"topic b" placeholders improved performance for every model.
  • About 15–20% of goals remained unreached, which the authors attribute to the lack of an explicit multi-turn policy. The dataset and baselines are public in the PaddlePaddle models repository on GitHub.

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

📚 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 Wenquan Wu, Zhen Guo, Xiangyang Zhou, Hua Wu, Xiyuan Zhang, Rongzhong Lian and Haifeng Wang. 2019. Proactive Human-Machine Conversation with Explicit Conversation Goal. 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/p19-1369

@inproceedings{wu2019proactive,
  title = {{Proactive Human-Machine Conversation with Explicit Conversation Goal}},
  author = {Wenquan Wu, Zhen Guo, Xiangyang Zhou, Hua Wu, Xiyuan Zhang, Rongzhong Lian and Haifeng Wang},
  booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  year = {2019},
  doi = {10.18653/v1/p19-1369},
  url = {https://doi.org/10.18653/v1/p19-1369}
}

References

23 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Antoine Bordes, Y-Lan Boureau, and Jason Weston. 2016. Learning end-to-end goal-oriented dialog. arXiv preprint arXiv:1605.07683. 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. J.L. Fleiss et al. 1971. Measuring nominal scale agreement among many raters. Psychological Bulletin, 76(5):378–382. find
  4. Marjan Ghazvininejad, Chris Brockett, Ming-Wei Chang, Bill Dolan, Jianfeng Gao, Wen-tau Yih, and Michel Galley. 2018. A knowledge-grounded neural conversation model. In Thirty-Second AAAI Conference on Artificial Intelligence. find
  5. Raymond Li, Samira Ebrahimi Kahou, Hannes Schulz, Vincent Michalski, Laurent Charlin, and Chris Pal. 2018. Towards deep conversational recommendations. In Advances in Neural Information Processing Systems, pages 9748–9758. find
  6. Shuman Liu, Hongshen Chen, Zhaochun Ren, Yang Feng, Qun Liu, and Dawei Yin. 2018. Knowledge diffusion for neural dialogue generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1489–1498. find
  7. Kaixiang Mo, Yu Zhang, Shuangyin Li, Jiajun Li, and Qiang Yang. 2018. Personalizing a dialogue system with transfer reinforcement learning. In Thirty-Second AAAI Conference on Artificial Intelligence. find
  8. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. our card
  9. Nikita Moghe, Siddhartha Arora, Suman Banerjee, and Mitesh M. Khapra. 2018. Towards exploiting background knowledge for building conversation systems. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2322–2332. our card
  10. Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, and Jason Weston. 2019. Wizard of wikipedia: Knowledge-powered conversational agents. In International Conference on Learning Representations. find
  11. Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in pytorch. In NIPS-W. with deep attention matching network. In Proceedings of the 56th Annual Meeting of the Association f… find
  12. Alan M Turing. 2009. Computing machinery and intelligence. In Parsing the Turing Test, pages 23–65. find
  13. Pavlos Vougiouklis, Jonathon Hare, and Elena Simperl. 2016. A neural network approach for knowledge-driven response generation. In Proceedings of COL-ING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3370–3380. find
  14. Wenya Zhu, Kaixiang Mo, Yu Zhang, Zhangbin Zhu, Xuezheng Peng, and Qiang Yang. 2017. Flexible end-to-end dialogue system for knowledge grounded conversation. CoRR. find
  15. 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 the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2193–2203. find
  16. Yu Wu, Wei Wu, Ming Zhou, and Zhoujun Li. 2017. Sequential match network: A new architecture for multi-turn response selection in retrieval-based chatbots. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 372–381. find
  17. Lili Yao, Yaoyuan Zhang, Yansong Feng, Dongyan Zhao, and Rui Yan. 2017. Towards implicit content-introducing for generative short-text conversation systems. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2190–2199. find
  18. Jun Yin, Xin Jiang, Zhengdong Lu, Lifeng Shang, Hang Li, and Xiaoming Li. 2015. Neural generative question answering. CoRR, abs/1512.01337. find
  19. Steve Young, Milica Gašić, Blaise Thomson, and Jason D Williams. 2013. Pomdp-based statistical spoken dialog systems: A review. Proceedings of the IEEE, 101(5):1160–1179. find
  20. 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? In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2204– 2213. our card
  21. Tiancheng Zhao, Ran Zhao, and Maxine Eskenazi. 2017. Learning discourse-level diversity for neural dialog models using conditional variational autoencoders. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 654–664, Vancouver, C… our card
  22. Hao Zhou, Tom Young, Minlie Huang, Haizhou Zhao, Jingfang Xu, and Xiaoyan Zhu. 2018a. Commonsense knowledge aware conversation generation with graph attention. In Proceedings of the 27th International Joint Conference on Artificial Intelligence, pages 4623–4629. find
  23. Xiangyang Zhou, Lu Li, Daxiang Dong, Yi Liu, Ying Chen, Wayne Xin Zhao, Dianhai Yu, and Hua Wu. 2018b. Multi-turn response selection for chatbots find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wu-2019-proactive-human-machine-conversation-explicit/