Representations for Question Answering from Documents with Tables and Text

TL;DR

This paper enhances question answering from web tables by integrating surrounding textual context to refine table representations and combining text and table-based predictions, leading to improved accuracy on the Natural Questions dataset.

Contribution

It introduces a method to incorporate textual context into table representations and combines predictions from text and tables for better QA performance.

Findings

Significant improvements on the Natural Questions dataset.

Effective integration of text and table information.

Enhanced table representations with surrounding text.

Abstract

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.