Open Domain Question Answering over Tables via Dense Retrieval
Open Domain Question Answering over Tables via Dense Retrieval
复制标题
通过密集检索在表上进行开放域问答
DOI：
10.18653/v1/2021.naacl-main.43
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Julian Martin Eisenschlos
中科院分区：
文献类型：
--
作者：
Jonathan Herzig;Thomas Müller;Syrine Krichene;Julian Martin Eisenschlos
开放领域问答的最新进展导致了基于密集检索的强大模型，但仅专注于检索文本段落。在这项工作中，我们首次解决了开放领域的表格QA，并证明了通过设计用于处理表格上下文的检索器可以改进检索。我们为我们的检索者提供了一种有效的预训练过程，并利用挖掘的硬负片来提高检索质量。由于缺少相关数据集，我们将自然问题的子集(Kwiatkowski等人，2019年)提取到表QA数据集中。我们发现，与基于BERT的检索器相比，我们的检索器将检索结果从72.0提高到81.1 Recall@10，并将端到端QA结果从33.8提高到37.7。
Recent advances in open-domain QA have led to strong models based on dense retrieval, but only focused on retrieving textual passages. In this work, we tackle open-domain QA over tables for the first time, and show that retrieval can be improved by a retriever designed to handle tabular context. We present an effective pre-training procedure for our retriever and improve retrieval quality with mined hard negatives. As relevant datasets are missing, we extract a subset of Natural Questions (Kwiatkowski et al., 2019) into a Table QA dataset. We find that our retriever improves retrieval results from 72.0 to 81.1 recall@10 and end-to-end QA results from 33.8 to 37.7 exact match, over a BERT based retriever.