2kenize: Tying Subword Sequences for Chinese Script Conversion
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
2kenize : Tying Subword Sequences for Chinese Script Conversion. / A, Pranav; Augenstein, Isabelle.
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2020. p. 7257-7272.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - 2kenize
T2 - 58th Annual Meeting of the Association for Computational Linguistics
AU - A, Pranav
AU - Augenstein, Isabelle
PY - 2020
Y1 - 2020
N2 - Simplified Chinese to Traditional Chinese character conversion is a common preprocessing step in Chinese NLP. Despite this, current approaches have insufficient performance because they do not take into account that a simplified Chinese character can correspond to multiple traditional characters. Here, we propose a model that can disambiguate between mappings and convert between the two scripts. The model is based on subword segmentation, two language models, as well as a method for mapping between subword sequences. We further construct benchmark datasets for topic classification and script conversion. Our proposed method outperforms previous Chinese Character conversion approaches by 6 points in accuracy. These results are further confirmed in a downstream application, where 2kenize is used to convert pretraining dataset for topic classification. An error analysis reveals that our method’s particular strengths are in dealing with code mixing and named entities.
AB - Simplified Chinese to Traditional Chinese character conversion is a common preprocessing step in Chinese NLP. Despite this, current approaches have insufficient performance because they do not take into account that a simplified Chinese character can correspond to multiple traditional characters. Here, we propose a model that can disambiguate between mappings and convert between the two scripts. The model is based on subword segmentation, two language models, as well as a method for mapping between subword sequences. We further construct benchmark datasets for topic classification and script conversion. Our proposed method outperforms previous Chinese Character conversion approaches by 6 points in accuracy. These results are further confirmed in a downstream application, where 2kenize is used to convert pretraining dataset for topic classification. An error analysis reveals that our method’s particular strengths are in dealing with code mixing and named entities.
U2 - 10.18653/v1/2020.acl-main.648
DO - 10.18653/v1/2020.acl-main.648
M3 - Article in proceedings
SP - 7257
EP - 7272
BT - Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
PB - Association for Computational Linguistics
Y2 - 5 July 2020 through 10 July 2020
ER -
ID: 255044965