all AI news
History-Aware Conversational Dense Retrieval. (arXiv:2401.16659v1 [cs.IR])
cs.CL updates on arXiv.org arxiv.org
Conversational search facilitates complex information retrieval by enabling
multi-turn interactions between users and the system. Supporting such
interactions requires a comprehensive understanding of the conversational
inputs to formulate a good search query based on historical information. In
particular, the search query should include the relevant information from the
previous conversation turns. However, current approaches for conversational
dense retrieval primarily rely on fine-tuning a pre-trained ad-hoc retriever
using the whole conversational search session, which can be lengthy and noisy.
Moreover, existing …
arxiv conversation conversational conversational search cs.ir current enabling good history information inputs interactions query retrieval search understanding