Representations for Question Answering from Documents with Tables and Text
This addresses the challenge of interpreting succinct table information in web documents for question answering, though it is incremental in combining existing methods.
The paper tackled the problem of question answering from documents containing tables and text by refining table representations using surrounding textual context, achieving significant improvements on the Natural Questions dataset.
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.