arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.09889cs.IRcs.AIcs.CL
收藏

表检索是一个已解决的问题吗?探索具备连接感知的多表检索

Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval

MIT(麻省理工学院);AWS AI Labs(亚马逊云科技人工智能实验室)

Peter Baile Chen, Yi Zhang, Dan Roth

AI总结:

针对多表问答中检索需考虑隐式连接计划的问题,提出基于混合整数规划的连接感知重排序方法,同时建模表-查询与表-表相关性,显著提升表检索和端到端QA性能。

摘要:

在基于表回答给定问题时,检索包含必要信息的相关表对于开放域问答(QA)系统至关重要。以往方法假设此类问题的答案要么可以在单个表中找到,要么可以在通过问题分解或重写识别出的多个表中找到。然而,这两种方法都不充分,因为许多问题需要检索多个表,并通过无法从用户查询本身辨别的连接计划将它们连接起来。如果在检索阶段不考虑连接计划,那么随后基于这些检索到的表进行推理和回答的步骤很可能是错误的。为解决这一问题,我们提出了一种在表检索过程中为任意查询和数据库发掘有用连接关系的方法。我们采用一种新颖的重排序方法,将其表述为混合整数规划,该方法不仅考虑表与查询的相关性,还考虑需要推断连接关系的表与表之间的相关性。我们的方法在表检索方面的F1分数最高优于最先进方法9.3%,在端到端QA方面的准确率最高优于最先进方法5.4%。

英文摘要:

Retrieving relevant tables containing the necessary information to accurately answer a given question over tables is critical to open-domain question-answering (QA) systems. Previous methods assume the answer to such a question can be found either in a single table or multiple tables identified through question decomposition or rewriting. However, neither of these approaches is sufficient, as many questions require retrieving multiple tables and joining them through a join plan that cannot be discerned from the user query itself. If the join plan is not considered in the retrieval stage, the subsequent steps of reasoning and answering based on those retrieved tables are likely to be incorrect. To address this problem, we introduce a method that uncovers useful join relations for any query and database during table retrieval. We use a novel re-ranking method formulated as a mixed-integer program that considers not only table-query relevance but also table-table relevance that requires inferring join relationships. Our method outperforms the state-of-the-art approaches for table retrieval by up to 9.3% in F1 score and for end-to-end QA by up to 5.4% in accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑