论文标题
XTQA：教科书问题的跨度级解释回答
XTQA: Span-Level Explanations of the Textbook Question Answering
论文作者
论文摘要
教科书问题回答（TQA）是一项任务，应该回答一个图表/非三图问题，因为大型多模式上下文由大量的论文和图表组成。我们认为，这项任务的解释性应将学生视为要考虑的关键方面。为了解决这个问题，我们根据提议的粗到精细的粒度算法，将新颖的架构朝着TQA（XTQA）的跨度解释进行了设计，该算法不仅可以提供答案，还可以提供跨度级别的证据，以选择它们为学生选择它们。该算法首先精心选择了使用TF-IDF方法与问题相关的顶级$ M $段落，然后通过将每个阶段的所有候选者跨度从所有候选者跨越的范围中精心选择，通过将每个跨度的信息获取到问题中的所有段落中的所有范围。实验结果表明，与基准相比，XTQA显着提高了最先进的性能。源代码可在https://github.com/keep-smile-001/opentqa上找到
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
