Using BERT for choosing classifiers in Mandarin

International Conference on Natural Language Generation, pp. 172–176

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.

Authors 4

1. Jani Järnfors Aachen

   Leiden University · Utrecht University

   Affiliation as printed

   Utrecht University ♣ Leiden University

2. Guanyi Chen Aachen

   Leiden University · Utrecht University

   Affiliation as printed

   Utrecht University ♣ Leiden University

3. Kees van Deemter Aachen

   Leiden University · Utrecht University

   Affiliation as printed

   Utrecht University ♣ Leiden University

4. Rint Sybesma Aachen

   Leiden University · Utrecht University

   Affiliation as printed

   Utrecht University ♣ Leiden University