RoCEL: Advancing Table Entity Linking through Distinctive Row and Column Contexts

Yuanzheng Wang, Yixing Fan, Jiafeng Guo, Ruqing Zhang, Xueqi Cheng


Abstract
Table entity linking (TEL) aims to map entity mentions in the table to their corresponding entities in a knowledge base (KB). The core of this task is to leverage structured contexts, specifically row and column contexts, to enhance the semantics of mentions in entity disambiguation. Most entity linking (EL) methods primarily focus on understanding sequential text contexts, making it difficult to adapt to the row and column structure of tables. Additionally, existing methods for TEL indiscriminately mix row and column contexts together, overlooking their semantic differences. In this paper, we explicitly distinguish the modeling of row and column contexts, and propose a method called RoCEL to capture their distinct semantics. Specifically, for row contexts in tables, we take the attention mechanism to learn the implicit relational dependencies between each cell and the mention. For column contexts in tables, we employ a set-wise encoder to learn the categorical information about the group of mentions. At last, we merge both contexts to obtain the final mention embedding for link prediction. Experiments on four benchmarks show that our approach outperforms the state-of-the-art (SOTA) baseline by about 1.5% on the in-domain dataset, and by 3.7% on average across three out-of-domain datasets.
Anthology ID:
2024.emnlp-main.853
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15284–15298
Language:
URL:
https://aclanthology.org/2024.emnlp-main.853
DOI:
Bibkey:
Cite (ACL):
Yuanzheng Wang, Yixing Fan, Jiafeng Guo, Ruqing Zhang, and Xueqi Cheng. 2024. RoCEL: Advancing Table Entity Linking through Distinctive Row and Column Contexts. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 15284–15298, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
RoCEL: Advancing Table Entity Linking through Distinctive Row and Column Contexts (Wang et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.853.pdf