Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfer

Elizabeth Salesky, Neha Verma, Philipp Koehn, Matt Post

Submission Type: Regular Long Paper

Submission Track: Machine Translation

Submission Track 2: Multilinguality and Linguistic Diversity

Keywords: machine translation, pixel representations, multilinguality, cross-lingual transfer, unseen scripts

TL;DR: We use pixel representations to remove the vocabulary bottleneck for multilingual translation models, resulting in more effective and efficient cross-lingual transfer within and across scripts.

Abstract: We introduce and demonstrate how to effectively train multilingual machine translation models with pixel representations. We experiment with two different data settings with a variety of language and script coverage, demonstrating improved performance compared to subword embeddings. We explore various properties of pixel representations such as parameter sharing within and across scripts to better understand where they lead to positive transfer. We observe that these properties not only enable seamless cross-lingual transfer to unseen scripts, but make pixel representations more data-efficient than alternatives such as vocabulary expansion. We hope this work contributes to more extensible multilingual models for all languages and scripts.

Submission Number: 25