Dense Retrieval Adaptation using Target Domain Description

TL;DR

This paper proposes a new zero-shot domain adaptation method for dense retrieval models using only a textual description of the target domain, creating synthetic data to improve retrieval performance.

Contribution

It introduces a novel adaptation approach that leverages domain descriptions to generate synthetic data, enabling effective domain adaptation without access to target documents.

Findings

Synthetic data improves retrieval in new domains

Method outperforms baseline zero-shot approaches

Effective across diverse target domains

Abstract

In information retrieval (IR), domain adaptation is the process of adapting a retrieval model to a new domain whose data distribution is different from the source domain. Existing methods in this area focus on unsupervised domain adaptation where they have access to the target document collection or supervised (often few-shot) domain adaptation where they additionally have access to (limited) labeled data in the target domain. There also exists research on improving zero-shot performance of retrieval models with no adaptation. This paper introduces a new category of domain adaptation in IR that is as-yet unexplored. Here, similar to the zero-shot setting, we assume the retrieval model does not have access to the target document collection. In contrast, it does have access to a brief textual description that explains the target domain. We define a taxonomy of domain attributes in retrieval tasks to understand different properties of a source domain that can be adapted to a target domain. We introduce a novel automatic data construction pipeline that produces a synthetic document collection, query set, and pseudo relevance labels, given a textual domain description. Extensive experiments on five diverse target domains show that adapting dense retrieval models using the constructed synthetic data leads to effective retrieval performance on the target domain.