Abstract
Using neural networks to generate replies in human-computer dialogue systems is attracting increasing attention over the past few years. However, the performance is not satisfactory: the neural network tends to generate safe, universally relevant replies which carry little meaning. In this paper, we propose a content-introducing approach to neural network-based generative dialogue systems. We first use pointwise mutual information (PMI) to predict a noun as a keyword, reflecting the main gist of the reply. We then propose seq2BF, a “sequence to backward and forward sequences” model, which generates a reply containing the given keyword. Experimental results show that our approach significantly outperforms traditional sequence-to-sequence models in terms of human evaluation and the entropy measure, and that the predicted keyword can appear at an appropriate position in the reply.- Anthology ID:
- C16-1316
- Volume:
- Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
- Month:
- December
- Year:
- 2016
- Address:
- Osaka, Japan
- Editors:
- Yuji Matsumoto, Rashmi Prasad
- Venue:
- COLING
- SIG:
- Publisher:
- The COLING 2016 Organizing Committee
- Note:
- Pages:
- 3349–3358
- Language:
- URL:
- https://aclanthology.org/C16-1316
- DOI:
- Cite (ACL):
- Lili Mou, Yiping Song, Rui Yan, Ge Li, Lu Zhang, and Zhi Jin. 2016. Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3349–3358, Osaka, Japan. The COLING 2016 Organizing Committee.
- Cite (Informal):
- Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation (Mou et al., COLING 2016)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/C16-1316.pdf