mlsanityData to 7 Oct 2026

The University of Edinburgh's Submission to the WMT22 Code-Mixing Shared Task (MixMT)

arXiv 2210.11309 ↗First posted 20 Oct 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

The University of Edinburgh participated in the WMT22 shared task on code-mixed translation. This consists of two subtasks: i) generating code-mixed Hindi/English (Hinglish) text generation from parallel Hindi and English sentences and ii) machine translation from Hinglish to English. As both subtasks are considered low-resource, we focused our efforts on careful data generation and curation, especially the use of backtranslation from monolingual resources. For subtask 1 we explored the effects of constrained decoding on English and transliterated subwords in order to produce Hinglish. For subtask 2, we investigated different pretraining techniques, namely comparing simple initialisation from existing machine translation models and aligned augmentation. For both subtasks, we found that our baseline systems worked best. Our systems for both subtasks were one of the overall top-performing submissions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 53 references that are in the map. First posted on arXiv 20 Oct 2022.

Builds on

26 of 53 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  3. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  4. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  5. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  6. 2019Cross-lingual Language Model Pretrainingcited by 1,088
  7. 2020Language-agnostic BERT Sentence Embeddingcited by 621
  8. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 556
  9. 2017Word Translation Without Parallel Datacited by 480
  10. 2017Lexically Constrained Decoding for Sequence Generation Using Grid Beam Searchcited by 234
  11. 2019WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipediacited by 221
  12. 2018Marian: Fast Neural Machine Translation in C++cited by 202
14 more
  1. 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 181
  2. 2021Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languagescited by 133
  3. 2021Contrastive Learning for Many-to-many Multilingual Neural Machine Translationcited by 108
  4. 2019A Survey of Code-switched Speech and Language Processingcited by 73
  5. 2020Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Informationcited by 64
  6. 2020Code-switching pre-training for neural machine translationcited by 43
  7. 2019On The Evaluation of Machine Translation Systems Trained With Back-Translationcited by 40
  8. 2020PHINC: A Parallel Hinglish Social Media Code-Mixed Corpus for Machine Translationcited by 38
  9. 2018Neural Machine Translation Decoding with Terminology Constraintscited by 36
  10. 2022L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Modelscited by 33
  11. 2019A Call for Prudent Choice of Subword Merge Operations in Neural Machine Translationcited by 30
  12. 2021HinGE: A Dataset for Generation and Evaluation of Code-Mixed Hinglish Textcited by 28
  13. 2022Universal Conditional Masked Language Pre-training for Neural Machine Translationcited by 12
  14. 2017Efficient Twitter Sentiment Classification using Subjective Distant Supervisioncited by 9

Built on by

Not cited yet.