arXiv Open Access 2022

Impact of Domain-Adapted Multilingual Neural Machine Translation in the Medical Domain

Miguel Rios Raluca-Maria Chereji Alina Secara Dragos Ciobanu

Lihat Sumber

Abstrak

Multilingual Neural Machine Translation (MNMT) models leverage many language pairs during training to improve translation quality for low-resource languages by transferring knowledge from high-resource languages. We study the quality of a domain-adapted MNMT model in the medical domain for English-Romanian with automatic metrics and a human error typology annotation which includes terminology-specific error categories. We compare the out-of-domain MNMT with the in-domain adapted MNMT. The in-domain MNMT model outperforms the out-of-domain MNMT in all measured automatic metrics and produces fewer terminology errors.

Topik & Kata Kunci

cs.CL

Penulis (4)

Miguel Rios

Raluca-Maria Chereji

Alina Secara

Dragos Ciobanu

Format Sitasi

APA MLA BibTeX

Rios, M., Chereji, R., Secara, A., Ciobanu, D. (2022). Impact of Domain-Adapted Multilingual Neural Machine Translation in the Medical Domain. https://arxiv.org/abs/2212.02143

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2022
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓