MLR: A Two-stage Conversational Query Rewriting Model with Multi-task Learning
This work addresses the problem of conversational context understanding for dialogue systems, offering an incremental improvement by integrating word category information into query rewriting.
The paper tackles the challenge of multi-turn conversational query understanding in open domains by proposing MLR, a two-stage model that rewrites multi-turn queries into single-turn queries using multi-task learning. Experimental results on a new Chinese dataset show that MLR outperforms compared models, demonstrating improved rewriting performance through word category information.
Conversational context understanding aims to recognize the real intention of user from the conversation history, which is critical for building the dialogue system. However, the multi-turn conversation understanding in open domain is still quite challenging, which requires the system extracting the important information and resolving the dependencies in contexts among a variety of open topics. In this paper, we propose the conversational query rewriting model - MLR, which is a Multi-task model on sequence Labeling and query Rewriting. MLR reformulates the multi-turn conversational queries into a single turn query, which conveys the true intention of users concisely and alleviates the difficulty of the multi-turn dialogue modeling. In the model, we formulate the query rewriting as a sequence generation problem and introduce word category information via the auxiliary word category label predicting task. To train our model, we construct a new Chinese query rewriting dataset and conduct experiments on it. The experimental results show that our model outperforms compared models, and prove the effectiveness of the word category information in improving the rewriting performance.