Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914666516578304 |
|---|---|
| author | Khiu, Eric Toossi, Hasti Anugraha, David Liu, Jinyu Li, Jiaxu Flores, Juan Armando Parra Roman, Leandro Acros Doğruöz, A. Seza Lee, En-Shiun Annie |
| author_facet | Khiu, Eric Toossi, Hasti Anugraha, David Liu, Jinyu Li, Jiaxu Flores, Juan Armando Parra Roman, Leandro Acros Doğruöz, A. Seza Lee, En-Shiun Annie |
| contents | Fine-tuning and testing a multilingual large language model is expensive and challenging for low-resource languages (LRLs). While previous studies have predicted the performance of natural language processing (NLP) tasks using machine learning methods, they primarily focus on high-resource languages, overlooking LRLs and shifts across domains. Focusing on LRLs, we investigate three factors: the size of the fine-tuning corpus, the domain similarity between fine-tuning and testing corpora, and the language similarity between source and target languages. We employ classical regression models to assess how these factors impact the model's performance. Our results indicate that domain similarity has the most critical impact on predicting the performance of Machine Translation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_02633 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity Khiu, Eric Toossi, Hasti Anugraha, David Liu, Jinyu Li, Jiaxu Flores, Juan Armando Parra Roman, Leandro Acros Doğruöz, A. Seza Lee, En-Shiun Annie Computation and Language Machine Learning Fine-tuning and testing a multilingual large language model is expensive and challenging for low-resource languages (LRLs). While previous studies have predicted the performance of natural language processing (NLP) tasks using machine learning methods, they primarily focus on high-resource languages, overlooking LRLs and shifts across domains. Focusing on LRLs, we investigate three factors: the size of the fine-tuning corpus, the domain similarity between fine-tuning and testing corpora, and the language similarity between source and target languages. We employ classical regression models to assess how these factors impact the model's performance. Our results indicate that domain similarity has the most critical impact on predicting the performance of Machine Translation models. |
| title | Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2402.02633 |