English

The Effect of Alignment Objectives on Code-Switching Translation

Computation and Language 2023-09-12 v1

Abstract

One of the things that need to change when it comes to machine translation is the models' ability to translate code-switching content, especially with the rise of social media and user-generated content. In this paper, we are proposing a way of training a single machine translation model that is able to translate monolingual sentences from one language to another, along with translating code-switched sentences to either language. This model can be considered a bilingual model in the human sense. For better use of parallel data, we generated synthetic code-switched (CSW) data along with an alignment loss on the encoder to align representations across languages. Using the WMT14 English-French (En-Fr) dataset, the trained model strongly outperforms bidirectional baselines on code-switched translation while maintaining quality for non-code-switched (monolingual) data.

Keywords

Cite

@article{arxiv.2309.05044,
  title  = {The Effect of Alignment Objectives on Code-Switching Translation},
  author = {Mohamed Anwar},
  journal= {arXiv preprint arXiv:2309.05044},
  year   = {2023}
}

Comments

This paper was originally submitted on 30/06/2022

R2 v1 2026-06-28T12:17:23.343Z