Zero-shot Neural Passage Retrieval via Domain-targeted Synthetic Question Generation

Ji Ma, Ivan Korotkov, Yinfei Yang, Keith Hall, Ryan McDonald


Abstract
A major obstacle to the wide-spread adoption of neural retrieval models is that they require large supervised training sets to surpass traditional term-based techniques, which are constructed from raw corpora. In this paper, we propose an approach to zero-shot learning for passage retrieval that uses synthetic question generation to close this gap. The question generation system is trained on general domain data, but is applied to documents in the targeted domain. This allows us to create arbitrarily large, yet noisy, question-passage relevance pairs that are domain specific. Furthermore, when this is coupled with a simple hybrid term-neural model, first-stage retrieval performance can be improved further. Empirically, we show that this is an effective strategy for building neural passage retrieval models in the absence of large training corpora. Depending on the domain, this technique can even approach the accuracy of supervised models.
Anthology ID:
2021.eacl-main.92
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1075–1088
Language:
URL:
https://aclanthology.org/2021.eacl-main.92
DOI:
10.18653/v1/2021.eacl-main.92
Bibkey:
Cite (ACL):
Ji Ma, Ivan Korotkov, Yinfei Yang, Keith Hall, and Ryan McDonald. 2021. Zero-shot Neural Passage Retrieval via Domain-targeted Synthetic Question Generation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1075–1088, Online. Association for Computational Linguistics.
Cite (Informal):
Zero-shot Neural Passage Retrieval via Domain-targeted Synthetic Question Generation (Ma et al., EACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2021.eacl-main.92.pdf
Data
BioASQNatural Questions