Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917595427373056 |
|---|---|
| author | Zhu, Fengbin Wang, Chao Feng, Fuli Ren, Zifeng Li, Moxin Chua, Tat-Seng |
| author_facet | Zhu, Fengbin Wang, Chao Feng, Fuli Ren, Zifeng Li, Moxin Chua, Tat-Seng |
| contents | Discrete reasoning over table-text documents (e.g., financial reports) gains increasing attention in recent two years. Existing works mostly simplify this challenge by manually selecting and transforming document pages to structured tables and paragraphs, hindering their practical application. In this work, we explore a more realistic problem setting in the form of TAT-DQA, i.e. to answer the question over a visually-rich table-text document. Specifically, we propose a novel Doc2SoarGraph framework with enhanced discrete reasoning capability by harnessing the differences and correlations among different elements (e.g., quantities, dates) of the given question and document with Semantic-oriented hierarchical Graph structures. We conduct extensive experiments on TAT-DQA dataset, and the results show that our proposed framework outperforms the best baseline model by 17.73% and 16.91% in terms of Exact Match (EM) and F1 score respectively on the test set, achieving the new state-of-the-art. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_01938 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs Zhu, Fengbin Wang, Chao Feng, Fuli Ren, Zifeng Li, Moxin Chua, Tat-Seng Computation and Language Artificial Intelligence Discrete reasoning over table-text documents (e.g., financial reports) gains increasing attention in recent two years. Existing works mostly simplify this challenge by manually selecting and transforming document pages to structured tables and paragraphs, hindering their practical application. In this work, we explore a more realistic problem setting in the form of TAT-DQA, i.e. to answer the question over a visually-rich table-text document. Specifically, we propose a novel Doc2SoarGraph framework with enhanced discrete reasoning capability by harnessing the differences and correlations among different elements (e.g., quantities, dates) of the given question and document with Semantic-oriented hierarchical Graph structures. We conduct extensive experiments on TAT-DQA dataset, and the results show that our proposed framework outperforms the best baseline model by 17.73% and 16.91% in terms of Exact Match (EM) and F1 score respectively on the test set, achieving the new state-of-the-art. |
| title | Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2305.01938 |