Multi-task Retrieval for Knowledge-Intensive Tasks
Jean Maillard Vladimir Karpukhin* Fabio Petroni Wen-tau Yih Barlas Oğuz Veselin Stoyanov Gargi Ghosh Facebook AI Equal Contribution.
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.
中文速览
从大规模语料库中检索相关段落是开放域问答、事实核查等知识密集型任务的关键环节，但现有神经检索模型（如DPR）一旦跨领域使用性能就会大幅下降，在样本稀少时更是不如传统的BM25方法。为此，研究者提出了一种多任务联合训练的通用神经检索器（Universal Retriever），在涵盖问答、事实核查、对话等五类任务的KILT基准上同时训练同一个双编码器模型，并结合对抗式难负样本挖掘来进一步提升表现。实验结果表明，该通用检索器在少样本场景下超越了以往方法，在有充足领域数据的场景下也能与专门训练的检索器持平甚至更优，并在多个下游任务上达到或刷新了最优水平。这项工作的意义在于：它证明了一个单一模型可以像BM25那样开箱即用、跨任务稳健，同时又保留了神经检索在特定领域精调后的高性能优势，为构建实用的多任务知识密集型系统提供了坚实基础。
原文 arXiv:2101.00117;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2101.00117v1