arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.04053cs.CLcs.AIcs.LG
收藏

基于表的事实验证与显著性感知学习

Table-based Fact Verification with Salience-aware Learning

University of Southern California(南加州大学)

Fei Wang, Kexuan Sun, Jay Pujara, Pedro Szekely, Muhao Chen

摘要:

表格提供了可用于验证文本语句的有价值的知识。虽然一些作品已经考虑了基于表格的事实验证,但表格数据与文本语句中的标记的直接对齐很少可用。此外,训练一个广义的事实验证模型需要大量的标记训练数据。在本文中,我们提出了一个新的系统来解决这些问题。受反事实因果关系的启发,我们的系统通过基于探测的显著性估计来识别语句中的标记级显著性。显著性估计允许从两个角度增强对事实验证的学习。从一个角度来看,我们的系统进行掩蔽的显着标记预测,以增强表和语句之间的对齐和推理模型。从另一个角度来看,我们的系统应用显着感知数据增强,通过替换非显着术语来生成更多样化的训练实例集。TabFact上的实验结果表明,所提出的显着性感知学习技术的有效改善,导致新的SOTA性能的基准。我们的代码可在https://github.com/luka-group/Salience-aware-Learning上公开获取。

英文摘要:

Tables provide valuable knowledge that can be used to verify textual statements. While a number of works have considered table-based fact verification, direct alignments of tabular data with tokens in textual statements are rarely available. Moreover, training a generalized fact verification model requires abundant labeled training data. In this paper, we propose a novel system to address these problems. Inspired by counterfactual causality, our system identifies token-level salience in the statement with probing-based salience estimation. Salience estimation allows enhanced learning of fact verification from two perspectives. From one perspective, our system conducts masked salient token prediction to enhance the model for alignment and reasoning between the table and the statement. From the other perspective, our system applies salience-aware data augmentation to generate a more diverse set of training instances by replacing non-salient terms. Experimental results on TabFact show the effective improvement by the proposed salience-aware learning techniques, leading to the new SOTA performance on the benchmark. Our code is publicly available at https://github.com/luka-group/Salience-aware-Learning .

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。

↑