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.
Cite
CITATION STYLE
Fang, B., Druckenbrodt, C., Akhondi, S. A., He, J., Baldwin, T., & Verspoor, K. (2021). ChEMU-Ref: A corpus for modeling anaphora resolution in the chemical domain. In EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference (pp. 1362–1375). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.eacl-main.116
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
