Choosing between long and short word forms in Mandarin

Lin Li; Kees van Deemter; Denis Paperno; Jingyu Fan

doi:10.18653/v1/W19-8605

Choosing between long and short word forms in Mandarin

Lin Li, Kees van Deemter, Denis Paperno, Jingyu Fan

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

Abstract

Between 80% and 90% of all Chinese words have long and short form such as 老虎/虎 (laohu/hu , tiger) (Duanmu, 2013). Consequently, the choice between long and short forms is a key problem for lexical choice across NLP and NLG in Chinese. Following on from earlier work on abbreviations in English (Mahowald et al., 2013), we bring a probabilistic perspective to word length choice, using both a behavioural and a corpus-based approach. Thus, we hypothesise that, in Chinese, short forms are likelier in supportive than in neutral contexts. Our corpus and behavioral study supported this hypothesis, but a closer analysis revealed striking differences between different types of Chinese words.

Original language	English
Title of host publication	Proceedings of the 12th International Conference on Natural Language Generation
Publisher	Association for Computational Linguistics
Pages	34-39
Number of pages	6
DOIs	https://doi.org/10.18653/v1/W19-8605
Publication status	Published - 1 Oct 2019

Access to Document

10.18653/v1/W19-8605Licence: CC BY

W19-8605Final published version, 463 KBLicence: CC BY

Cite this

@inproceedings{306c75a6b1ec4c73acacf7493ad8da85,

title = "Choosing between long and short word forms in Mandarin",

abstract = "Between 80% and 90% of all Chinese words have long and short form such as 老虎/虎 (laohu/hu , tiger) (Duanmu, 2013). Consequently, the choice between long and short forms is a key problem for lexical choice across NLP and NLG in Chinese. Following on from earlier work on abbreviations in English (Mahowald et al., 2013), we bring a probabilistic perspective to word length choice, using both a behavioural and a corpus-based approach. Thus, we hypothesise that, in Chinese, short forms are likelier in supportive than in neutral contexts. Our corpus and behavioral study supported this hypothesis, but a closer analysis revealed striking differences between different types of Chinese words.",

author = "Lin Li and {van Deemter}, Kees and Denis Paperno and Jingyu Fan",

year = "2019",

month = oct,

day = "1",

doi = "10.18653/v1/W19-8605",

language = "English",

pages = "34--39",

booktitle = "Proceedings of the 12th International Conference on Natural Language Generation",

publisher = "Association for Computational Linguistics",

address = "United States",

}

TY - GEN

T1 - Choosing between long and short word forms in Mandarin

AU - Li, Lin

AU - van Deemter, Kees

AU - Paperno, Denis

AU - Fan, Jingyu

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Between 80% and 90% of all Chinese words have long and short form such as 老虎/虎 (laohu/hu , tiger) (Duanmu, 2013). Consequently, the choice between long and short forms is a key problem for lexical choice across NLP and NLG in Chinese. Following on from earlier work on abbreviations in English (Mahowald et al., 2013), we bring a probabilistic perspective to word length choice, using both a behavioural and a corpus-based approach. Thus, we hypothesise that, in Chinese, short forms are likelier in supportive than in neutral contexts. Our corpus and behavioral study supported this hypothesis, but a closer analysis revealed striking differences between different types of Chinese words.

AB - Between 80% and 90% of all Chinese words have long and short form such as 老虎/虎 (laohu/hu , tiger) (Duanmu, 2013). Consequently, the choice between long and short forms is a key problem for lexical choice across NLP and NLG in Chinese. Following on from earlier work on abbreviations in English (Mahowald et al., 2013), we bring a probabilistic perspective to word length choice, using both a behavioural and a corpus-based approach. Thus, we hypothesise that, in Chinese, short forms are likelier in supportive than in neutral contexts. Our corpus and behavioral study supported this hypothesis, but a closer analysis revealed striking differences between different types of Chinese words.

U2 - 10.18653/v1/W19-8605

DO - 10.18653/v1/W19-8605

M3 - Conference contribution

SP - 34

EP - 39

BT - Proceedings of the 12th International Conference on Natural Language Generation

PB - Association for Computational Linguistics

ER -

Choosing between long and short word forms in Mandarin

Abstract

Access to Document

Fingerprint

Cite this