ChEMU-Ref: A Corpus for Modeling Anaphora Resolution in the Chemical Domain

Biaoyan Fang, Christian Druckenbrodt, Saber A Akhondi, Jiayuan He, Timothy Baldwin, Karin Verspoor


Abstract
Chemical patents contain rich coreference and bridging links, which are the target of this research. Specially, we introduce a novel annotation scheme, based on which we create the ChEMU-Ref dataset from reaction description snippets in English-language chemical patents. We propose a neural approach to anaphora resolution, which we show to achieve strong results, especially when jointly trained over coreference and bridging links.
Anthology ID:
2021.eacl-main.116
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1362–1375
Language:
URL:
https://aclanthology.org/2021.eacl-main.116
DOI:
10.18653/v1/2021.eacl-main.116
Bibkey:
Cite (ACL):
Biaoyan Fang, Christian Druckenbrodt, Saber A Akhondi, Jiayuan He, Timothy Baldwin, and Karin Verspoor. 2021. ChEMU-Ref: A Corpus for Modeling Anaphora Resolution in the Chemical Domain. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1362–1375, Online. Association for Computational Linguistics.
Cite (Informal):
ChEMU-Ref: A Corpus for Modeling Anaphora Resolution in the Chemical Domain (Fang et al., EACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.eacl-main.116.pdf
Code
 biaoyanf/chemu-ref