DUQGen: Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation

arXiv:2404.02489v1 Announce Type: cross
Abstract: State-of-the-art neural rankers pre-trained on large task-specific training data such as MS-MARCO, have been shown to exhibit strong performance on various ranking tasks without domain adaptation, also called zero-shot. However, zero-shot neural ranking may be sub-optimal, as it does not take advantage of the target domain information. Unfortunately, acquiring sufficiently large and high quality target training data to improve a modern neural ranker can be costly and time-consuming. To address this problem, we propose a …

abstract art arxiv cs.cl cs.ir data domain domain adaptation however performance query ranking state synthetic tasks task-specific training training training data type unsupervised zero-shot