TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance
This work addresses a neglected real-world problem in finance by providing a challenging benchmark for QA models, though it is incremental in advancing existing QA methods.
The authors tackled the problem of question answering over hybrid tabular and textual data, such as financial reports, by creating the TAT-QA dataset and proposing the TAGOP model, which achieved 58.0% F1, an 11.1% absolute improvement over previous baselines but still far behind human performance of 90.8% F1.
Hybrid data combining both tabular and textual content (e.g., financial reports) are quite pervasive in the real world. However, Question Answering (QA) over such hybrid data is largely neglected in existing research. In this work, we extract samples from real financial reports to build a new large-scale QA dataset containing both Tabular And Textual data, named TAT-QA, where numerical reasoning is usually required to infer the answer, such as addition, subtraction, multiplication, division, counting, comparison/sorting, and the compositions. We further propose a novel QA model termed TAGOP, which is capable of reasoning over both tables and text. It adopts sequence tagging to extract relevant cells from the table along with relevant spans from the text to infer their semantics, and then applies symbolic reasoning over them with a set of aggregation operators to arrive at the final answer. TAGOPachieves 58.0% inF1, which is an 11.1% absolute increase over the previous best baseline model, according to our experiments on TAT-QA. But this result still lags far behind performance of expert human, i.e.90.8% in F1. It is demonstrated that our TAT-QA is very challenging and can serve as a benchmark for training and testing powerful QA models that address hybrid form data.