Abstract
Search-oriented conversational systems rely on information needs expressed in natural language (NL). We focus here on the understanding of NL expressions for building keyword-based queries. We propose a reinforcement-learning-driven translation model framework able to 1) learn the translation from NL expressions to queries in a supervised way, and, 2) to overcome the lack of large-scale dataset by framing the translation model as a word selection approach and injecting relevance feedback as a reward in the learning process. Experiments are carried out on two TREC datasets. We outline the effectiveness of our approach.- Anthology ID:
- W18-5705
- Volume:
- Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI
- Month:
- October
- Year:
- 2018
- Address:
- Brussels, Belgium
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 33–39
- Language:
- URL:
- https://aclanthology.org/W18-5705
- DOI:
- 10.18653/v1/W18-5705
- Cite (ACL):
- Wafa Aissa, Laure Soulier, and Ludovic Denoyer. 2018. A Reinforcement Learning-driven Translation Model for Search-Oriented Conversational Systems. In Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI, pages 33–39, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- A Reinforcement Learning-driven Translation Model for Search-Oriented Conversational Systems (Aissa et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/W18-5705.pdf