MULTITAT: Benchmarking Multilingual Table-and-Text Question Answering
This addresses a gap for researchers and practitioners in multilingual NLP by providing a benchmark for TATQA, though it is incremental as it builds on existing datasets through translation.
The authors tackled the lack of multilingual datasets for table-and-text question answering (TATQA) by creating MULTITAT, a dataset translated into 10 languages from existing English sources, and found that model performance drops by an average of 19.4% on non-English data compared to English.
Question answering on the hybrid context of tables and text (TATQA) is a critical task, with broad applications in data-intensive domains. However, existing TATQA datasets are limited to English, leading to several drawbacks: (i) They overlook the challenges of multilingual TAT-QA and cannot assess model performance in the multilingual setting. (ii) They do not reflect real-world scenarios where tables and texts frequently appear in non-English languages. To address the limitations, we propose the first multilingual TATQA dataset (MULTITAT). Specifically, we sample data from 3 mainstream TATQA datasets and translate it into 10 diverse languages. To align the model TATQA capabilities in English with other languages, we develop a baseline, Ours. Experimental results reveal that the performance on non-English data in MULTITAT drops by an average of 19.4% compared to English, proving the necessity of MULTITAT. We further analyze the reasons for this performance gap. Furthermore, Ours outperforms other baselines by an average of 3.3, demonstrating its effectiveness.