TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data

TL;DR

TaCube pre-computes numerical data over tables to enhance PLMs' ability to answer numerical reasoning questions, significantly improving accuracy on benchmarks like TAT-QA and WikiTQ.

Contribution

It introduces a pre-computation method that covers various arithmetic operations over table segments, boosting PLMs' numerical reasoning performance.

Findings

F1 score on TAT-QA improved from 49.6% to 66.2%.

Achieved state-of-the-art 59.6% denotation accuracy on WikiTQ.

Significant gains in numerical reasoning accuracy, e.g., +39.6% on sum.

Abstract

Existing auto-regressive pre-trained language models (PLMs) like T5 and BART, have been well applied to table question answering by UNIFIEDSKG and TAPEX, respectively, and demonstrated state-of-the-art results on multiple benchmarks. However, auto-regressive PLMs are challenged by recent emerging numerical reasoning datasets, such as TAT-QA, due to the error-prone implicit calculation. In this paper, we present TaCube, to pre-compute aggregation/arithmetic results for the table in advance, so that they are handy and readily available for PLMs to answer numerical reasoning questions. TaCube systematically and comprehensively covers a collection of computational operations over table segments. By simply concatenating TaCube to the input sequence of PLMs, it shows significant experimental effectiveness. TaCube promotes the F1 score from 49.6% to 66.2% on TAT-QA and achieves new state-of-the-art results on WikiTQ (59.6% denotation accuracy). TaCube's improvements on numerical reasoning cases are even more notable: on TAT-QA, TaCube promotes the exact match accuracy of BART-large by 39.6% on sum, 52.5% on average, 36.6% on substraction, and 22.2% on division. We believe that TaCube is a general and portable pre-computation solution that can be potentially integrated to various numerical reasoning frameworks