mlsanityData to 14 Oct 2026

Code-Switching for Enhancing NMT with Pre-Specified Translation

arXiv 1904.09107 ↗First posted 19 Apr 2019cs.CLcited by 53

Not on the map. Why?

Abstract (arXiv)

Leveraging user-provided translation to constrain NMT has practical significance. Existing methods can be classified into two main categories, namely the use of placeholder tags for lexicon words and the use of hard constraints during decoding. Both methods can hurt translation fidelity for various reasons. We investigate a data augmentation method, making code-switched training data by replacing source phrases with their target translations. Our method does not change the MNT model or decoding algorithm, allowing the model to learn lexicon translations by copying source-side target words. Extensive experiments show that our method achieves consistent improvements over existing approaches, improving translation of constrained words without hurting unconstrained words.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 16; 2022: 15; 2023: 12; 2024: 4; 2025: 6.

53 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  2. 2021Survey of Low-Resource Machine Translationcited by 92
  3. 2023Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translationcited by 74
  4. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  5. 2022End-to-End Speech Translation for Code Switched Speechcited by 26
  6. 2022General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretrainingcited by 25
  7. 2023Gender Neutralization for an Inclusive Machine Translation: from Theoretical Foundations to Open Challengescited by 22
  8. 2021Can You Traducir This? Machine Translation for Code-Switched Inputcited by 21
  9. 2021TranSmart: A Practical Interactive Machine Translation Systemcited by 17
  10. 2022CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translationcited by 17
  11. 2023Chain-of-Dictionary Prompting Elicits Translation in Large Language Modelscited by 16
  12. 2022ArzEn-ST: A Three-way Speech Translation Corpus for Code-Switched Egyptian Arabic - Englishcited by 13
38 more
  1. 2021Encouraging Neural Machine Translation to Satisfy Terminology Constraintscited by 10
  2. 2022Improving Automated Program Repair with Domain Adaptationcited by 10
  3. 2023WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Predictioncited by 10
  4. 2022Integrating Vectorized Lexical Constraints for Neural Machine Translationcited by 9
  5. 2022Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentationcited by 9
  6. 2024Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Modelscited by 9
  7. 2021WeTS: A Benchmark for Translation Suggestioncited by 8
  8. 2023Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translationcited by 8
  9. 2021GWLAN: General Word-Level AutocompletioN for Computer-Aided Translationcited by 7
  10. 2022Exploring Segmentation Approaches for Neural Machine Translation of Code-Switched Egyptian Arabic-English Textcited by 7
  11. 2021End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languagescited by 6
  12. 2021Input Augmentation Improves Constrained Beam Search for Neural Machine Translation: NTT at WAT 2021cited by 4
  13. 2022DICTDIS: Dictionary Constrained Disambiguation for Improved NMTcited by 4
  14. 2024Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Modelscited by 4
  15. 2021Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Predictioncited by 3
  16. 2021Rule-based Morphological Inflection Improves Neural Terminology Translationcited by 3
  17. 2022Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraintscited by 3
  18. 2022Data-adaptive Transfer Learning for Translation: A Case Study in Haitian and Jamaicancited by 3
  19. 2022Checks and Strategies for Enabling Code-Switched Machine Translationcited by 3
  20. 2023Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraintscited by 3
  21. 2023Data Augmentation Techniques for Machine Translation of Code-Switched Texts: A Comparative Studycited by 3
  22. 2024Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approachcited by 3
  23. 2025Low-resource Machine Translation for Code-switched Kazakh-Russian Language Paircited by 3
  24. 2025DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translationcited by 3
  25. 2021CUNI systems for WMT21: Terminology translation Shared Taskcited by 2
  26. 2021One Source, Two Targets: Challenges and Rewards of Dual Decodingcited by 2
  27. 2021Lingua Custodia's participation at the WMT 2021 Machine Translation using Terminologies shared taskcited by 2
  28. 2021Modeling Target-side Inflection in Placeholder Translationcited by 1
  29. 2023Disambiguated Lexically Constrained Neural Machine Translationcited by 1
  30. 2023Negative Lexical Constraints in Neural Machine Translationcited by 1
  31. 2023The Effect of Alignment Objectives on Code-Switching Translationcited by 1
  32. 2024CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Unitscited by 1
  33. 2025PHRASED: Phrase Dictionary Biasing for Speech Translationcited by 1
  34. 2021Bilingual Terminology Extraction from Comparable E-Commerce Corporacited by 0
  35. 2022A Template-based Method for Constrained Neural Machine Translationcited by 0
  36. 2022Domain Curricula for Code-Switched MT at MixMT 2022cited by 0
  37. 2023Evaluating, Understanding, and Improving Constrained Text Generation for Large Language Modelscited by 0
  38. 2023Improving Neural Machine Translation by Multi-Knowledge Integration with Promptingcited by 0

50 most cited of 53 All 53 (JSON)