[go: up one dir, main page]

How Robust Are the QA Models for Hybrid Scientific Tabular Data? A Study Using Customized Dataset

Akash Ghosh, Venkata Sahith Bathini, Niloy Ganguly, Pawan Goyal, Mayank Singh


Abstract
Question-answering (QA) on hybrid scientific tabular and textual data deals with scientific information, and relies on complex numerical reasoning. In recent years, while tabular QA has seen rapid progress, understanding their robustness on scientific information is lacking due to absence of any benchmark dataset. To investigate the robustness of the existing state-of-the-art QA models on scientific hybrid tabular data, we propose a new dataset, “SciTabQA”, consisting of 822 question-answer pairs from scientific tables and their descriptions. With the help of this dataset, we assess the state-of-the-art Tabular QA models based on their ability (i) to use heterogeneous information requiring both structured data (table) and unstructured data (text) and (ii) to perform complex scientific reasoning tasks. In essence, we check the capability of the models to interpret scientific tables and text. Our experiments show that “SciTabQA” is an innovative dataset to study question-answering over scientific heterogeneous data. We benchmark three state-of-the-art Tabular QA models, and find that the best F1 score is only 0.462.
Anthology ID:
2024.lrec-main.724
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
8258–8264
Language:
URL:
https://aclanthology.org/2024.lrec-main.724
DOI:
Bibkey:
Cite (ACL):
Akash Ghosh, Venkata Sahith Bathini, Niloy Ganguly, Pawan Goyal, and Mayank Singh. 2024. How Robust Are the QA Models for Hybrid Scientific Tabular Data? A Study Using Customized Dataset. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 8258–8264, Torino, Italia. ELRA and ICCL.
Cite (Informal):
How Robust Are the QA Models for Hybrid Scientific Tabular Data? A Study Using Customized Dataset (Ghosh et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.724.pdf