Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfer

作     者：Salesky, Elizabeth Verma, Neha Koehn, Philipp Post, Matt 

作者机构：Johns Hopkins University United States Human Language Technology Center of Excellence United States Microsoft United States 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2023年

核心收录：

主　　题：Pixels 

摘      要：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. Copyright © 2023, The Authors. All rights reserved.