ConvGQR: Generative Query Reformulation for Conversational Search
This work addresses the challenge of query reformulation for conversational search systems, offering a method to enhance search accuracy without expensive re-training, though it is incremental in nature.
The paper tackles the problem of generating effective search queries in conversational search by proposing ConvGQR, a framework that uses generative pre-trained language models for query rewriting and answer generation, resulting in improved retrieval performance as demonstrated on four datasets.
In conversational search, the user's real search intent for the current turn is dependent on the previous conversation history. It is challenging to determine a good search query from the whole conversation context. To avoid the expensive re-training of the query encoder, most existing methods try to learn a rewriting model to de-contextualize the current query by mimicking the manual query rewriting. However, manually rewritten queries are not always the best search queries. Training a rewriting model on them would limit the model's ability to produce good search queries. Another useful hint is the potential answer to the question. In this paper, we propose ConvGQR, a new framework to reformulate conversational queries based on generative pre-trained language models (PLMs), one for query rewriting and another for generating potential answers. By combining both, ConvGQR can produce better search queries. In addition, to relate query reformulation to retrieval performance, we propose a knowledge infusion mechanism to optimize both query reformulation and retrieval. Extensive experiments on four conversational search datasets demonstrate the effectiveness of ConvGQR.