Grammatical Error Correction for Code-Switched Sentences by Learners of English
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910562364948480 |
|---|---|
| author | Chan, Kelvin Wey Han Bryant, Christopher Nguyen, Li Caines, Andrew Yuan, Zheng |
| author_facet | Chan, Kelvin Wey Han Bryant, Christopher Nguyen, Li Caines, Andrew Yuan, Zheng |
| contents | Code-switching (CSW) is a common phenomenon among multilingual speakers where multiple languages are used in a single discourse or utterance. Mixed language utterances may still contain grammatical errors however, yet most existing Grammar Error Correction (GEC) systems have been trained on monolingual data and not developed with CSW in mind. In this work, we conduct the first exploration into the use of GEC systems on CSW text. Through this exploration, we propose a novel method of generating synthetic CSW GEC datasets by translating different spans of text within existing GEC corpora. We then investigate different methods of selecting these spans based on CSW ratio, switch-point factor and linguistic constraints, and identify how they affect the performance of GEC systems on CSW text. Our best model achieves an average increase of 1.57 $F_{0.5}$ across 3 CSW test sets (English-Chinese, English-Korean and English-Japanese) without affecting the model's performance on a monolingual dataset. We furthermore discovered that models trained on one CSW language generalise relatively well to other typologically similar CSW languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_12489 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Grammatical Error Correction for Code-Switched Sentences by Learners of English Chan, Kelvin Wey Han Bryant, Christopher Nguyen, Li Caines, Andrew Yuan, Zheng Computation and Language Code-switching (CSW) is a common phenomenon among multilingual speakers where multiple languages are used in a single discourse or utterance. Mixed language utterances may still contain grammatical errors however, yet most existing Grammar Error Correction (GEC) systems have been trained on monolingual data and not developed with CSW in mind. In this work, we conduct the first exploration into the use of GEC systems on CSW text. Through this exploration, we propose a novel method of generating synthetic CSW GEC datasets by translating different spans of text within existing GEC corpora. We then investigate different methods of selecting these spans based on CSW ratio, switch-point factor and linguistic constraints, and identify how they affect the performance of GEC systems on CSW text. Our best model achieves an average increase of 1.57 $F_{0.5}$ across 3 CSW test sets (English-Chinese, English-Korean and English-Japanese) without affecting the model's performance on a monolingual dataset. We furthermore discovered that models trained on one CSW language generalise relatively well to other typologically similar CSW languages. |
| title | Grammatical Error Correction for Code-Switched Sentences by Learners of English |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.12489 |