Conversational search provides a natural interface for information retrieval (IR). Recent approaches have demonstrated promising results in applying dense retrieval to conversational IR. However, training dense retrievers requires large amounts of in-domain paired data. This hinders the development of conversational dense retrievers, as abundant in-domain conversations are expensive to collect. In this paper, we propose CONVERSER, a framework for training conversational dense retrievers with at most 6 examples of in-domain dialogues. Specifically, we utilize the in-context learning capability of large language models to generate conversational queries given a passage in the retrieval corpus. Experimental results on conversational retrieval benchmarks OR-QuAC and TREC CAsT 19 show that the proposed CONVERSER achieves comparable performance to fully-supervised models, demonstrating the effectiveness of our proposed framework in few-shot conversational dense retrieval. All source code and generated datasets are available at https://github.com/MiuLab/CONVERSER
@article{arxiv.2309.06748,
title = {CONVERSER: Few-Shot Conversational Dense Retrieval with Synthetic Data Generation},
author = {Chao-Wei Huang and Chen-Yu Hsu and Tsu-Yuan Hsu and Chen-An Li and Yun-Nung Chen},
journal= {arXiv preprint arXiv:2309.06748},
year = {2023}
}