Unknown Script: Impact of Script on Cross-Lingual Transfer
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917659011973120 |
|---|---|
| author | Tufa, Wondimagegnhue Tsegaye Markov, Ilia Vossen, Piek |
| author_facet | Tufa, Wondimagegnhue Tsegaye Markov, Ilia Vossen, Piek |
| contents | Cross-lingual transfer has become an effective way of transferring knowledge between languages. In this paper, we explore an often overlooked aspect in this domain: the influence of the source language of a language model on language transfer performance. We consider a case where the target language and its script are not part of the pre-trained model. We conduct a series of experiments on monolingual and multilingual models that are pre-trained on different tokenization methods to determine factors that affect cross-lingual transfer to a new language with a unique script. Our findings reveal the importance of the tokenizer as a stronger factor than the shared script, language similarity, and model size. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_18810 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unknown Script: Impact of Script on Cross-Lingual Transfer Tufa, Wondimagegnhue Tsegaye Markov, Ilia Vossen, Piek Computation and Language Cross-lingual transfer has become an effective way of transferring knowledge between languages. In this paper, we explore an often overlooked aspect in this domain: the influence of the source language of a language model on language transfer performance. We consider a case where the target language and its script are not part of the pre-trained model. We conduct a series of experiments on monolingual and multilingual models that are pre-trained on different tokenization methods to determine factors that affect cross-lingual transfer to a new language with a unique script. Our findings reveal the importance of the tokenizer as a stronger factor than the shared script, language similarity, and model size. |
| title | Unknown Script: Impact of Script on Cross-Lingual Transfer |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.18810 |