Title
Synthetic Target Domain Supervision for Open Retrieval QA
Abstract
ABSTRACTNeural passage retrieval is a new and promising approach in open retrieval question answering. In this work, we stress-test the Dense Passage Retriever (DPR)---a state-of-the-art (SOTA) open domain neural retrieval model---on closed and specialized target domains such as COVID-19, and find that it lags behind standard BM25 in this important real-world setting. To make DPR more robust under domain shift, we explore its fine-tuning with synthetic training examples, which we generate from unlabeled target domain text using a text-to-text generator. In our experiments, this noisy but fully automated target domain supervision gives DPR a sizable advantage over BM25 in out-of-domain settings, making it a more viable model in practice. Finally, an ensemble of BM25 and our improved DPR model yields the best results, further pushing the SOTA for open retrieval QA on multiple out-of-domain test sets.
Year
DOI
Venue
2021
10.1145/3404835.3463085
Research and Development in Information Retrieval
Keywords
DocType
Citations 
Open retrieval question answering, Neural passage retrieval, Weak supervision, Out-of-domain neural IR
Conference
1
PageRank 
References 
Authors
0.48
0
8
Name
Order
Citations
PageRank
Revanth Gangi Reddy111.83
Bhavani Iyer210.82
Md. Arafat Sultan3859.26
R. Zhang449042.39
Avi Sil511.83
Vittorio Castelli6928129.71
Tahira Naseem713.19
Salim Roukos86248845.50