Synthetic Context with LLM for Entity Linking from Scientific Tables

Yuji Oshima, Hiroyuki Shindo, Hiroki Teranishi, Hiroki Ouchi, Taro Watanabe


Abstract
Tables in scientific papers contain crucial information, such as experimental results.Entity Linking (EL) is a promising technology that analyses tables and associates them with a knowledge base.EL for table cells requires identifying the referent concept of each cell while understanding the context relevant to each cell in the paper. However, extracting the relevant context from the paper is challenging because the relevant parts are scattered in the main text and captions.This study defines a rule-based method for extracting broad context from the main text, including table captions and sentences that mention the table.Furthermore, we propose synthetic context as a more refined context generated by large language models (LLMs).In a synthetic context, contexts from the entire paper are refined by summarizing, injecting supplemental knowledge, and clarifying the referent concept.We observe this approach improves accuracy for EL by more than 10 points on the S2abEL dataset, and our qualitative analysis suggests potential future works.
Anthology ID:
2024.sdp-1.19
Volume:
Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Tirthankar Ghosal, Amanpreet Singh, Anita Waard, Philipp Mayr, Aakanksha Naik, Orion Weller, Yoonjoo Lee, Shannon Shen, Yanxia Qin
Venues:
sdp | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
202–214
Language:
URL:
https://aclanthology.org/2024.sdp-1.19
DOI:
Bibkey:
Cite (ACL):
Yuji Oshima, Hiroyuki Shindo, Hiroki Teranishi, Hiroki Ouchi, and Taro Watanabe. 2024. Synthetic Context with LLM for Entity Linking from Scientific Tables. In Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024), pages 202–214, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Synthetic Context with LLM for Entity Linking from Scientific Tables (Oshima et al., sdp-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.sdp-1.19.pdf