XTQA：教材问答的跨度级解释
XTQA: Span-Level Explanations of the Textbook Question Answering
AI总结：
本文提出XTQA架构，通过TF-IDF粗筛段落并依据信息增益精选证据跨度，在回答TQA问题的同时为学生提供跨度级解释，并显著超越基线。
摘要：
教材问答（Textbook Question Answering，TQA）是一项任务，要求在由大量文章和图表组成的大型多模态上下文下，回答图表类或非图表类问题。我们认为，该任务的可解释性应将学生作为需要考虑的关键方面。为解决这一问题，我们基于所提出的由粗到细粒度算法，设计了一种面向TQA跨度级解释的新型架构XTQA，它不仅能为学生提供答案，还能提供选择这些答案的跨度级证据。该算法首先使用TF-IDF方法粗略选择与问题相关的前M个段落，随后通过计算每个跨度对问题的信息增益，从这些段落内的所有候选跨度中精细选择前K个证据跨度。实验结果表明，与基线相比，XTQA显著提升了当前最优性能。源代码可在https://github.com/keep-smile-001/opentqa获取。
英文摘要：
Textbook Question Answering (TQA) is a task that one should answer a diagram/non-diagram question given a large multi-modal context consisting of abundant essays and diagrams. We argue that the explainability of this task should place students as a key aspect to be considered. To address this issue, we devise a novel architecture towards span-level eXplanations of the TQA (XTQA) based on our proposed coarse-to-fine grained algorithm, which can provide not only the answers but also the span-level evidences to choose them for students. This algorithm first coarsely chooses top $M$ paragraphs relevant to questions using the TF-IDF method, and then chooses top $K$ evidence spans finely from all candidate spans within these paragraphs by computing the information gain of each span to questions. Experimental results shows that XTQA significantly improves the state-of-the-art performance compared with baselines. The source code is available at https://github.com/keep-smile-001/opentqa
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。
