Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network
Xiangyang Zhou, Lu Li, Daxiang Dong, Yi Liu, Ying Chen, Wayne Xin Zhao, Dianhai Yu, Hua Wu
Abstract
Human generates responses relying on semantic and functional dependencies, including coreference relation, among dialogue elements and their context. In this paper, we investigate matching a response with its multi-turn context using dependency information based entirely on attention. Our solution is inspired by the recently proposed Transformer in machine translation (Vaswani et al., 2017) and we extend the attention mechanism in two ways. First, we construct representations of text segments at different granularities solely with stacked self-attention. Second, we try to extract the truly matched segment pairs with attention across the context and response. We jointly introduce those two kinds of attention in one uniform neural network. Experiments on two large-scale multi-turn response selection tasks show that our proposed model significantly outperforms the state-of-the-art models.- Anthology ID:
- P18-1103
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1118–1127
- Language:
- URL:
- https://aclanthology.org/P18-1103
- DOI:
- 10.18653/v1/P18-1103
- Cite (ACL):
- Xiangyang Zhou, Lu Li, Daxiang Dong, Yi Liu, Ying Chen, Wayne Xin Zhao, Dianhai Yu, and Hua Wu. 2018. Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1118–1127, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network (Zhou et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/P18-1103.pdf
- Code
- baidu/Dialogue + additional community code
- Data
- Douban, Douban Conversation Corpus, RRS, UDC