论文标题
旨在解释BERT以阅读理解的质量检查
Towards Interpreting BERT for Reading Comprehension Based QA
论文作者
论文摘要
Bert及其变体在各种NLP任务中都达到了最先进的性能。从那时起，已经提出了各种作品来分析伯特中捕获的语言信息。但是，当前的作品并未提供有关伯特如何在阅读基于理解的问题回答任务上取得几乎人类水平的绩效的洞察力。在这项工作中，我们试图为RCQA解释BERT。由于BERT层没有预定义的角色，因此我们使用集成梯度来定义图层的角色或功能。根据定义的角色，我们对所有层进行初步分析。我们观察到，初始层的重点是查询 - 通用相互作用，而后来的层则更多地集中在上下文理解和增强答案预测上。特别是对于量词问题（多少/多少），我们注意到Bert专注于后来层的单词（即，段落中的其他数字数量）混淆，但仍然设法正确预测了答案。微调和分析脚本将在https://github.com/iitmnlp/bert-analysis-rcqa上公开获得。
BERT and its variants have achieved state-of-the-art performance in various NLP tasks. Since then, various works have been proposed to analyze the linguistic information being captured in BERT. However, the current works do not provide an insight into how BERT is able to achieve near human-level performance on the task of Reading Comprehension based Question Answering. In this work, we attempt to interpret BERT for RCQA. Since BERT layers do not have predefined roles, we define a layer's role or functionality using Integrated Gradients. Based on the defined roles, we perform a preliminary analysis across all layers. We observed that the initial layers focus on query-passage interaction, whereas later layers focus more on contextual understanding and enhancing the answer prediction. Specifically for quantifier questions (how much/how many), we notice that BERT focuses on confusing words (i.e., on other numerical quantities in the passage) in the later layers, but still manages to predict the answer correctly. The fine-tuning and analysis scripts will be publicly available at https://github.com/iitmnlp/BERT-Analysis-RCQA .
