Can You Traducir This? Machine Translation for Code-Switched Input
This addresses the problem of translating mixed-language texts for NLP applications, though it is incremental as it builds on existing data generation methods.
The paper tackled machine translation of code-switched texts by generating artificial training data from parallel texts, resulting in systems that outperform multilingual models for code-switched inputs.
Code-Switching (CSW) is a common phenomenon that occurs in multilingual geographic or social contexts, which raises challenging problems for natural language processing tools. We focus here on Machine Translation (MT) of CSW texts, where we aim to simultaneously disentangle and translate the two mixed languages. Due to the lack of actual translated CSW data, we generate artificial training data from regular parallel texts. Experiments show this training strategy yields MT systems that surpass multilingual systems for code-switched texts. These results are confirmed in an alternative task aimed at providing contextual translations for a L2 writing assistant.