Using BERT for choosing classifiers in Mandarin

Jani Järnfors; Guanyi Chen; Kees van Deemter; Rint Sybesma

Using BERT for choosing classifiers in Mandarin

Jani Järnfors
, Guanyi Chen
, Kees van Deemter
, Rint Sybesma

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

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.

Original language	English
Title of host publication	Proceedings of the 14th International Conference on Natural Language Generation
Place of Publication	Aberdeen, Scotland, UK
Publisher	Association for Computational Linguistics
Pages	172-176
Number of pages	5
Publication status	Published - 1 Aug 2021

Access to Document

2021.inlg-1.17Final published version, 273 KBLicence: CC BY

https://aclanthology.org/2021.inlg-1.17Licence: CC BY

Cite this

@inproceedings{2a4e32a787f645d2998e6cf1f647c29c,

title = "Using BERT for choosing classifiers in Mandarin",

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.",

author = "Jani J{\"a}rnfors and Guanyi Chen and \{van Deemter\}, Kees and Rint Sybesma",

year = "2021",

month = aug,

day = "1",

language = "English",

pages = "172--176",

booktitle = "Proceedings of the 14th International Conference on Natural Language Generation",

publisher = "Association for Computational Linguistics",

address = "United States",

}

Using BERT for choosing classifiers in Mandarin. / Järnfors, Jani; Chen, Guanyi; van Deemter, Kees et al.
Proceedings of the 14th International Conference on Natural Language Generation. Aberdeen, Scotland, UK: Association for Computational Linguistics, 2021. p. 172-176.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Using BERT for choosing classifiers in Mandarin

AU - Järnfors, Jani

AU - Chen, Guanyi

AU - van Deemter, Kees

AU - Sybesma, Rint

PY - 2021/8/1

Y1 - 2021/8/1

N2 - 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.

AB - 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.

M3 - Conference contribution

SP - 172

EP - 176

BT - Proceedings of the 14th International Conference on Natural Language Generation

PB - Association for Computational Linguistics

CY - Aberdeen, Scotland, UK

ER -

Using BERT for choosing classifiers in Mandarin

Abstract

Access to Document

Fingerprint

Cite this