TRAVEL: Tag-Aware Conversational FAQ Retrieval via Reinforcement Learning
Yue Chen, Dingnan Jin, Chen Huang, Jia Liu, Wenqiang Lei
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.
BibTeX
@inproceedings{
chen2023travel,
title={{TRAVEL}: Tag-Aware Conversational {FAQ} Retrieval via Reinforcement Learning},
author={Yue Chen and Dingnan Jin and Chen Huang and Jia Liu and Wenqiang Lei},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=kdjSXbypKX}
}