Chasing COMET: Leveraging Minimum Bayes Risk Decoding for Self-Improving Machine Translation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909207184277504 |
|---|---|
| author | Guttmann, Kamil Pokrywka, Mikołaj Charkiewicz, Adrian Nowakowski, Artur |
| author_facet | Guttmann, Kamil Pokrywka, Mikołaj Charkiewicz, Adrian Nowakowski, Artur |
| contents | This paper explores Minimum Bayes Risk (MBR) decoding for self-improvement in machine translation (MT), particularly for domain adaptation and low-resource languages. We implement the self-improvement process by fine-tuning the model on its MBR-decoded forward translations. By employing COMET as the MBR utility metric, we aim to achieve the reranking of translations that better aligns with human preferences. The paper explores the iterative application of this approach and the potential need for language-specific MBR utility metrics. The results demonstrate significant enhancements in translation quality for all examined language pairs, including successful application to domain-adapted models and generalisation to low-resource settings. This highlights the potential of COMET-guided MBR for efficient MT self-improvement in various scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_11937 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Chasing COMET: Leveraging Minimum Bayes Risk Decoding for Self-Improving Machine Translation Guttmann, Kamil Pokrywka, Mikołaj Charkiewicz, Adrian Nowakowski, Artur Computation and Language Artificial Intelligence Machine Learning This paper explores Minimum Bayes Risk (MBR) decoding for self-improvement in machine translation (MT), particularly for domain adaptation and low-resource languages. We implement the self-improvement process by fine-tuning the model on its MBR-decoded forward translations. By employing COMET as the MBR utility metric, we aim to achieve the reranking of translations that better aligns with human preferences. The paper explores the iterative application of this approach and the potential need for language-specific MBR utility metrics. The results demonstrate significant enhancements in translation quality for all examined language pairs, including successful application to domain-adapted models and generalisation to low-resource settings. This highlights the potential of COMET-guided MBR for efficient MT self-improvement in various scenarios. |
| title | Chasing COMET: Leveraging Minimum Bayes Risk Decoding for Self-Improving Machine Translation |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2405.11937 |