CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Units
Not on the map. Why?
Abstract (arXiv)
Multilingual code-switching research is often hindered by the lack and linguistically biased status of available datasets. To expand language representation, we synthesize code-switching data by replacing intonation units detected through PSST, a speech segmentation model fine-tuned from OpenAI's Whisper, using a speech-to-text translation dataset, CoVoST 2. With our dataset, CoVoSwitch, spanning 13 languages, we evaluate the code-switching translation performance of two multilingual translation models, M2M-100 418M and NLLB-200 600M. We reveal that the inclusion of code-switching units results in higher translation performance than monolingual settings and that models are better at code-switching translation into English than non-English. Further, low-resource languages gain most from integration of code-switched units when translating into English but much less when translating into non-English. Translations into low-resource languages also perform worse than even raw code-switched inputs. We find that systems excel at copying English tokens but struggle with non-English tokens, that the off-target problem in monolingual settings is also relevant in code-switching settings, and that models hallucinate in code-switching translation by introducing words absent in both of the original source sentences. CoVoSwitch and code are available at https://github.com/sophiayk20/covoswitch.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 24 of its 45 references that are in the map. First posted on arXiv 19 Jul 2024.
Builds on
24 of 45 references.
References · 24
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
- 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
- 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
- 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
- 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
- 2020Beyond English-Centric Multilingual Machine Translationcited by 559
- 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 556
- 2020Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translationcited by 277
- 2018Constituency Parsing with a Self-Attentive Encodercited by 196
- 2021Word Alignment by Fine-tuning Embeddings on Parallel Corporacited by 186
- 2023Hallucinations in Large Multilingual Translation Modelscited by 126
12 more
- 2018Multilingual Constituency Parsing with Self-Attention and Pre-Trainingcited by 117
- 2023Multilingual Large Language Models Are Not (Yet) Code-Switcherscited by 65
- 2019Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentencescited by 55
- 2019Code-Switching for Enhancing NMT with Pre-Specified Translationcited by 53
- 2021From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Textcited by 29
- 2022End-to-End Speech Translation for Code Switched Speechcited by 26
- 2021Can You Traducir This? Machine Translation for Code-Switched Inputcited by 21
- 2021On the Copying Behaviors of Pre-Training for Neural Machine Translationcited by 15
- 2023Towards a Better Understanding of Variations in Zero-Shot Neural Machine Translation Performancecited by 10
- 2023PSST! Prosodic Speech Segmentation with Transformerscited by 5
- 2023Towards Real-World Streaming Speech Translation for Code-Switched Speechcited by 4
- 2023On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Losscited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.