Open-WikiTable: Dataset for Open Domain Question Answering with Complex Reasoning over Table

TL;DR

Open-WikiTable is a new dataset for open domain question answering over tables that requires complex reasoning, such as aggregation and comparison, advancing research beyond simple cell retrieval.

Contribution

It introduces the first ODQA dataset that necessitates complex reasoning over tables, built on WikiSQL and WikiTableQuestions, enabling diverse research approaches.

Findings

Dataset enables complex reasoning tasks

Supports both textual answers and SQL queries

Facilitates future research in table-based ODQA

Abstract

Despite recent interest in open domain question answering (ODQA) over tables, many studies still rely on datasets that are not truly optimal for the task with respect to utilizing structural nature of table. These datasets assume answers reside as a single cell value and do not necessitate exploring over multiple cells such as aggregation, comparison, and sorting. Thus, we release Open-WikiTable, the first ODQA dataset that requires complex reasoning over tables. Open-WikiTable is built upon WikiSQL and WikiTableQuestions to be applicable in the open-domain setting. As each question is coupled with both textual answers and SQL queries, Open-WikiTable opens up a wide range of possibilities for future research, as both reader and parser methods can be applied. The dataset and code are publicly available.