Conference Proceedings

ChEMU-Ref: A corpus for modeling anaphora resolution in the chemical domain

B Fang, C Druckenbrodt, SA Akhondi, J He, T Baldwin, K Verspoor

EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference | Association for Computational Linguistics | Published : 2021

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.

University of Melbourne Researchers

Grants

Awarded by Australian Research Council


Funding Acknowledgements

Funding for the ChEMU project is provided by an Australian Research Council Linkage Project, project number LP160101469, and Elsevier. A graduate research scholarship is provided by Melbourne School of Engineering to Biaoyan Fang. We would also like to thank Dr. Meladel Mistica and our two chemical expert annotators Colleen Yeow Hui Shiuan and Sacha Novakovic for their contributions to refining the annotation guidelines.