Using BERT for choosing classifiers in Mandarin
Publication date
2021-08-01
Authors
Järnfors, Jani
Chen, Guanyi
van Deemter, Kees
Sybesma, Rint
Editors
Advisors
Supervisors
DOI
Document Type
Part of book
Metadata
Show full item recordCollections
License
cc_by
Abstract
Choosing the most suitable classifier in a linguistic context is a well-known problem in the production of Mandarin and many other languages. The present paper proposes a solution based on BERT, compares this solution to previous neural and rule-based models, and argues that the BERT model performs particularly well on those difficult cases where the classifier adds information to the text.
Keywords
Citation
Järnfors, J, Chen, G, van Deemter, K & Sybesma, R 2021, Using BERT for choosing classifiers in Mandarin. in Proceedings of the 14th International Conference on Natural Language Generation. Association for Computational Linguistics, Aberdeen, Scotland, UK, pp. 172-176. < https://aclanthology.org/2021.inlg-1.17 >