Character Set Construction for Chinese Language Learning

Chak Yan Yeung; John Lee

Character Set Construction for Chinese Language Learning

Department of Linguistics and Translation

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

85 Downloads (CityUHK Scholars)

Abstract

To promote efficient learning of Chinese characters, pedagogical materials may present not only a single character, but a set of characters that are related in meaning and in written form. This paper investigates automatic construction of these character sets. The proposed model represents a character as averaged word vectors of common words containing the character. It then identifies sets of characters with high semantic similarity through clustering. Human evaluation shows that this representation outperforms direct use of character embeddings, and that the resulting character sets capture distinct semantic ranges.

Original language	English
Title of host publication	Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications
Publisher	Association for Computational Linguistics
Pages	59–63
ISBN (Electronic)	978-1-954085-11-4
ISBN (Print)	9781954085114
Publication status	Published - 20 Apr 2021
Event	16th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2021) - Virtual Duration: 20 Apr 2021 → … https://sig-edu.org/bea/current

Conference

Conference	16th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2021)
Abbreviated title	BEA2021
Period	20/04/21 → …
Internet address	https://sig-edu.org/bea/current

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Access Output

78113214.pdfFinal Published version, 283 KBLicence: CC BY

https://www.aclweb.org/anthology/2021.bea-1.6/

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{266cbbdd018140349f18263e34d8ddf9,

title = "Character Set Construction for Chinese Language Learning",

abstract = "To promote efficient learning of Chinese characters, pedagogical materials may present not only a single character, but a set of characters that are related in meaning and in written form. This paper investigates automatic construction of these character sets. The proposed model represents a character as averaged word vectors of common words containing the character. It then identifies sets of characters with high semantic similarity through clustering. Human evaluation shows that this representation outperforms direct use of character embeddings, and that the resulting character sets capture distinct semantic ranges.",

author = "Yeung, {Chak Yan} and John Lee",

year = "2021",

month = apr,

day = "20",

language = "English",

isbn = "9781954085114",

pages = "59–63",

booktitle = "Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications",

publisher = "Association for Computational Linguistics",

address = "United States",

note = "16th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2021), BEA2021 ; Conference date: 20-04-2021",

url = "https://sig-edu.org/bea/current",

}

Yeung, CY & Lee, J 2021, Character Set Construction for Chinese Language Learning. in Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications. Association for Computational Linguistics, pp. 59–63, 16th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2021), 20/04/21. <https://www.aclweb.org/anthology/2021.bea-1.6/>

Character Set Construction for Chinese Language Learning. / Yeung, Chak Yan ; Lee, John.
Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications. Association for Computational Linguistics, 2021. p. 59–63.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Character Set Construction for Chinese Language Learning

AU - Yeung, Chak Yan

AU - Lee, John

PY - 2021/4/20

Y1 - 2021/4/20

N2 - To promote efficient learning of Chinese characters, pedagogical materials may present not only a single character, but a set of characters that are related in meaning and in written form. This paper investigates automatic construction of these character sets. The proposed model represents a character as averaged word vectors of common words containing the character. It then identifies sets of characters with high semantic similarity through clustering. Human evaluation shows that this representation outperforms direct use of character embeddings, and that the resulting character sets capture distinct semantic ranges.

AB - To promote efficient learning of Chinese characters, pedagogical materials may present not only a single character, but a set of characters that are related in meaning and in written form. This paper investigates automatic construction of these character sets. The proposed model represents a character as averaged word vectors of common words containing the character. It then identifies sets of characters with high semantic similarity through clustering. Human evaluation shows that this representation outperforms direct use of character embeddings, and that the resulting character sets capture distinct semantic ranges.

UR - http://www.scopus.com/inward/record.url?scp=85123936703&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85123936703&origin=recordpage

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781954085114

SP - 59

EP - 63

BT - Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications

PB - Association for Computational Linguistics

T2 - 16th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2021)

Y2 - 20 April 2021

ER -

Character Set Construction for Chinese Language Learning

Abstract

Conference

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this