mlsanityData to 14 Oct 2026

Domain Curricula for Code-Switched MT at MixMT 2022

arXiv 2210.17463 ↗First posted 31 Oct 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

In multilingual colloquial settings, it is a habitual occurrence to compose expressions of text or speech containing tokens or phrases of different languages, a phenomenon popularly known as code-switching or code-mixing (CMX). We present our approach and results for the Code-mixed Machine Translation (MixMT) shared task at WMT 2022: the task consists of two subtasks, monolingual to code-mixed machine translation (Subtask-1) and code-mixed to monolingual machine translation (Subtask-2). Most non-synthetic code-mixed data are from social media but gathering a significant amount of this kind of data would be laborious and this form of data has more writing variation than other domains, so for both subtasks, we experimented with data schedules for out-of-domain data. We jointly learn multiple domains of text by pretraining and fine-tuning, combined with a sentence alignment objective. We found that switching between domains caused improved performance in the domains seen earliest during training, but depleted the performance on the remaining domains. A continuous training run with strategically dispensed data of different domains showed a significantly improved performance over fine-tuning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 40 references that are in the map. First posted on arXiv 31 Oct 2022.

Builds on

22 of 40 references.

References · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  5. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  6. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  7. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 722
  8. 2019Pay Less Attention with Lightweight and Dynamic Convolutionscited by 211
  9. 2017The IIT Bombay English-Hindi Parallel Corpuscited by 75
  10. 2019A Survey of Code-switched Speech and Language Processingcited by 75
  11. 2020Balancing Training for Multilingual Neural Machine Translationcited by 72
  12. 2019The Missing Ingredient in Zero-Shot Neural Machine Translationcited by 59
10 more
  1. 2019Code-Switching for Enhancing NMT with Pre-Specified Translationcited by 53
  2. 2019Pretraining boosts out-of-domain robustness for pose estimationcited by 47
  3. 2020PHINC: A Parallel Hinglish Social Media Code-Mixed Corpus for Machine Translationcited by 38
  4. 2017Dynamic Data Selection for Neural Machine Translationcited by 33
  5. 2021HinGE: A Dataset for Generation and Evaluation of Code-Mixed Hinglish Textcited by 28
  6. 2021Can You Traducir This? Machine Translation for Code-Switched Inputcited by 21
  7. 2014BilBOWA: Fast Bilingual Distributed Representations without Word Alignmentscited by 16
  8. 2019Domain Differential Adaptation for Neural Machine Translationcited by 10
  9. 2016Trans-gram, Fast Cross-lingual Word-embeddingscited by 3
  10. 2022DaLC: Domain Adaptation Learning Curve Prediction for Neural Machine Translationcited by 2

Built on by

Not cited yet.