Enhancing Financial Table and Text Question Answering with Tabular Graph and Numerical Reasoning
Rungsiman Nararatwong, Natthawut Kertkeidkachorn, Ryutaro Ichise
Abstract
Typical financial documents consist of tables, texts, and numbers. Given sufficient training data, large language models (LM) can learn the tabular structures and perform numerical reasoning well in question answering (QA). However, their performances fall significantly when data and computational resources are limited. This study improves this performance drop by infusing explicit tabular structures through a graph neural network (GNN). We proposed a model developed from the baseline of a financial QA dataset named TAT-QA. The baseline model, TagOp, consists of answer span (evidence) extraction and numerical reasoning modules. As our main contributions, we introduced two components to the model: a GNN-based evidence extraction module for tables and an improved numerical reasoning module. The latter provides a solution to TagOp’s arithmetic calculation problem specific to operations requiring number ordering, such as subtraction and division, which account for a large portion of numerical reasoning. Our evaluation shows that the graph module has the advantage in low-resource settings, while the improved numerical reasoning significantly outperforms the baseline model.- Anthology ID:
- 2022.aacl-main.72
- Volume:
- Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2022
- Address:
- Online only
- Editors:
- Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
- Venues:
- AACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 991–1000
- Language:
- URL:
- https://aclanthology.org/2022.aacl-main.72
- DOI:
- Cite (ACL):
- Rungsiman Nararatwong, Natthawut Kertkeidkachorn, and Ryutaro Ichise. 2022. Enhancing Financial Table and Text Question Answering with Tabular Graph and Numerical Reasoning. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 991–1000, Online only. Association for Computational Linguistics.
- Cite (Informal):
- Enhancing Financial Table and Text Question Answering with Tabular Graph and Numerical Reasoning (Nararatwong et al., AACL-IJCNLP 2022)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2022.aacl-main.72.pdf