Multi-Task Retrieval for Knowledge-Intensive Tasks
Jean Maillard, Vladimir Karpukhin, Fabio Petroni, Wen-tau Yih, Barlas Oguz, Veselin Stoyanov, Gargi Ghosh
Abstract
Retrieving relevant contexts from a large corpus is a crucial step for tasks such as open-domain question answering and fact checking. Although neural retrieval outperforms traditional methods like tf-idf and BM25, its performance degrades considerably when applied to out-of-domain data. Driven by the question of whether a neural retrieval model can be _universal_ and perform robustly on a wide variety of problems, we propose a multi-task trained model. Our approach not only outperforms previous methods in the few-shot setting, but also rivals specialised neural retrievers, even when in-domain training data is abundant. With the help of our retriever, we improve existing models for downstream tasks and closely match or improve the state of the art on multiple benchmarks.
BibTeX
@inproceedings{maillard-etal-2021-multi,
title = "Multi-Task Retrieval for Knowledge-Intensive Tasks",
author = "Maillard, Jean and
Karpukhin, Vladimir and
Petroni, Fabio and
Yih, Wen-tau and
Oguz, Barlas and
Stoyanov, Veselin and
Ghosh, Gargi",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.89/",
doi = "10.18653/v1/2021.acl-long.89",
pages = "1098--1111"
}