Abstract
Efficiently retrieving FAQ questions that match users’ intent is essential for online customer service. Existing methods aim to fully utilize the dynamic conversation context to enhance the semantic association between the user query and FAQ questions. However, the conversation context contains noise, e.g., users may click questions they don’t like, leading to inaccurate semantics modeling. To tackle this, we introduce tags of FAQ questions, which can help us eliminate irrelevant information. We later integrate them into a reinforcement learning framework and minimize the negative impact of irrelevant information in the dynamic conversation context. We experimentally demonstrate our efficiency and effectiveness on conversational FAQ retrieval compared to other baselines.- Anthology ID:
- 2023.emnlp-main.234
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3861–3872
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.234
- DOI:
- 10.18653/v1/2023.emnlp-main.234
- Cite (ACL):
- Yue Chen, Dingnan Jin, Chen Huang, Jia Liu, and Wenqiang Lei. 2023. TRAVEL: Tag-Aware Conversational FAQ Retrieval via Reinforcement Learning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 3861–3872, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- TRAVEL: Tag-Aware Conversational FAQ Retrieval via Reinforcement Learning (Chen et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.emnlp-main.234.pdf