A Survey on Table Question Answering: Recent Advances

TL;DR

This survey reviews recent advances in Table Question Answering, categorizing methods, discussing datasets, challenges, and future research directions in this evolving field.

Contribution

It provides a comprehensive overview and classification of existing table QA methods, datasets, and highlights key challenges and future directions.

Findings

Classifies table QA methods into five categories

Identifies key challenges in current table QA approaches

Discusses potential future research directions

Abstract

Table Question Answering (Table QA) refers to providing precise answers from tables to answer a user's question. In recent years, there have been a lot of works on table QA, but there is a lack of comprehensive surveys on this research topic. Hence, we aim to provide an overview of available datasets and representative methods in table QA. We classify existing methods for table QA into five categories according to their techniques, which include semantic-parsing-based, generative, extractive, matching-based, and retriever-reader-based methods. Moreover, as table QA is still a challenging task for existing methods, we also identify and outline several key challenges and discuss the potential future directions of table QA.