2kenize: Tying Subword Sequences for Chinese Script Conversion
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- 2kenize
Forlagets udgivne version, 633 KB, PDF-dokument
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.
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics |
Forlag | Association for Computational Linguistics |
Publikationsdato | 2020 |
Sider | 7257-7272 |
DOI | |
Status | Udgivet - 2020 |
Begivenhed | 58th Annual Meeting of the Association for Computational Linguistics - Online Varighed: 5 jul. 2020 → 10 jul. 2020 |
Konference
Konference | 58th Annual Meeting of the Association for Computational Linguistics |
---|---|
By | Online |
Periode | 05/07/2020 → 10/07/2020 |
Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk
Ingen data tilgængelig
ID: 255044965