Investigating Lexical Sharing in Multilingual Machine Translation for Indian Languages - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Investigating Lexical Sharing in Multilingual Machine Translation for Indian Languages

Résumé

Multilingual language models have shown impressive cross-lingual transfer ability across a diverse set of languages and tasks. To improve the cross-lingual ability of these models, some strategies include transliteration and finer-grained segmentation into characters as opposed to subwords. In this work, we investigate lexical sharing in multilingual machine translation (MT) from Hindi, Gujarati, Nepali into English. We explore the trade-offs that exist in translation performance between data sampling and vocabulary size, and we explore whether transliteration is useful in encouraging cross-script generalisation. We also verify how the different settings generalise to unseen languages (Marathi and Bengali). We find that transliteration does not give pronounced improvements and our analysis suggests that our multilingual MT models trained on original scripts seem to already be robust to cross-script differences even for relatively low-resource languages. Our code will be made publicly available. 1

Dates et versions

hal-04093966 , version 1 (10-05-2023)

Licence

Paternité

Identifiants

Citer

Sonal Sannigrahi, Rachel Bawden. Investigating Lexical Sharing in Multilingual Machine Translation for Indian Languages. EAMT 2023 - 24th Annual Conference of the European Association for Machine Translation, Jun 2023, Tampere, Finland. ⟨hal-04093966⟩
10 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More