Representations for Question Answering from Documents with Tables and Text
Representations for Question Answering from Documents with Tables and Text
复制标题
带有表格和文本的文档问答的表示
DOI：
10.18653/v1/2021.eacl-main.253
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Mari Ostendorf
中科院分区：
文献类型：
--
作者：
V. Zayats;Kristina Toutanova;Mari Ostendorf
Web文档中的表格无处不在，可以直接用于回答在Web上搜索的许多查询，从而促进了它们在问题回答中的整合。通常，表格中的信息很简洁，很难用标准的语言表示法来解释。另一方面，表格通常出现在文本上下文中，例如描述表格的文章。使用项目中的信息作为附加上下文可能会丰富表的表示形式。在这项工作中，我们的目标是通过基于周围文本的信息提炼表格表示来改进来自表格的问题回答。我们还提出了一种有效的方法，将文本预测和基于表格的预测结合起来，从完整的文档中进行问题回答，在自然问题数据集上获得了显著的改进(Kwiatkowski等人，2019年)。
Tables in web documents are pervasive and can be directly used to answer many of the queries searched on the web, motivating their integration in question answering. Very often information presented in tables is succinct and hard to interpret with standard language representations. On the other hand, tables often appear within textual context, such as an article describing the table. Using the information from an article as additional context can potentially enrich table representations. In this work we aim to improve question answering from tables by refining table representations based on information from surrounding text. We also present an effective method to combine text and table-based predictions for question answering from full documents, obtaining significant improvements on the Natural Questions dataset (Kwiatkowski et al., 2019).