Modeling Multi-turn Conversation with Deep Utterance Aggregation
Zhuosheng Zhang, Jiangtong Li, Pengfei Zhu, Hai Zhao, Gongshen Liu
Abstract
Multi-turn conversation understanding is a major challenge for building intelligent dialogue systems. This work focuses on retrieval-based response matching for multi-turn conversation whose related work simply concatenates the conversation utterances, ignoring the interactions among previous utterances for context modeling. In this paper, we formulate previous utterances into context using a proposed deep utterance aggregation model to form a fine-grained context representation. In detail, a self-matching attention is first introduced to route the vital information in each utterance. Then the model matches a response with each refined utterance and the final matching score is obtained after attentive turns aggregation. Experimental results show our model outperforms the state-of-the-art methods on three multi-turn conversation benchmarks, including a newly introduced e-commerce dialogue corpus.- Anthology ID:
- C18-1317
- Volume:
- Proceedings of the 27th International Conference on Computational Linguistics
- Month:
- August
- Year:
- 2018
- Address:
- Santa Fe, New Mexico, USA
- Editors:
- Emily M. Bender, Leon Derczynski, Pierre Isabelle
- Venue:
- COLING
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3740–3752
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/C18-1317/
- DOI:
- Cite (ACL):
- Zhuosheng Zhang, Jiangtong Li, Pengfei Zhu, Hai Zhao, and Gongshen Liu. 2018. Modeling Multi-turn Conversation with Deep Utterance Aggregation. In Proceedings of the 27th International Conference on Computational Linguistics, pages 3740–3752, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
- Cite (Informal):
- Modeling Multi-turn Conversation with Deep Utterance Aggregation (Zhang et al., COLING 2018)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/C18-1317.pdf
- Code
- cooelf/DeepUtteranceAggregation
- Data
- E-commerce, Douban, Douban Conversation Corpus, UDC