mlsanityData to 13 Oct 2026

Training Neural Machine Translation To Apply Terminology Constraints

arXiv 1906.01105 ↗First posted 3 Jun 2019cs.CL cs.AI cs.LGcited by 73

Not on the map. Why?

Abstract (arXiv)

This paper proposes a novel method to inject custom terminology into neural machine translation at run time. Previous works have mainly proposed modifications to the decoding algorithm in order to constrain the output to include run-time-provided target terms. While being effective, these constrained decoding methods add, however, significant computational overhead to the inference step, and, as we show in this paper, can be brittle when tested in realistic conditions. In this paper we approach the problem by training a neural MT system to learn how to use custom terminology when provided with the input. Comparative experiments show that our method is not only more effective than a state-of-the-art implementation of constrained decoding, but is also as fast as constraint-free decoding.

Key facts. Cited by 73 papers in the map (data through 13 Oct 2026). First posted on arXiv 3 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 19; 2022: 11; 2023: 21; 2024: 7; 2025: 9; 2026: 6.

73 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,068
  2. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 154
  3. 2021Survey of Low-Resource Machine Translationcited by 92
  4. 2023Controlled Text Generation with Natural Language Instructionscited by 87
  5. 2023Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translationcited by 74
  6. 2023COLLIE: Systematic Construction of Constrained Text Generation Taskscited by 69
  7. 2022Gradient-Based Constrained Sampling from Language Modelscited by 64
  8. 2023Adaptive Machine Translation with Large Language Modelscited by 58
  9. 2023Benchmarking Machine Translation with Cultural Awarenesscited by 53
  10. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  11. 2021Controlling Conditional Language Models without Catastrophic Forgettingcited by 32
  12. 2022General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretrainingcited by 25
38 more
  1. 2023Gender Neutralization for an Inclusive Machine Translation: from Theoretical Foundations to Open Challengescited by 22
  2. 2021Can You Traducir This? Machine Translation for Code-Switched Inputcited by 21
  3. 2021Facilitating Terminology Translation with Target Lemma Annotationscited by 19
  4. 2023A Paradigm Shift: The Future of Machine Translation Lies with Large Language Modelscited by 19
  5. 2021TranSmart: A Practical Interactive Machine Translation Systemcited by 17
  6. 2023Domain Terminology Integration into Machine Translation: Leveraging Large Language Modelscited by 17
  7. 2023Chain-of-Dictionary Prompting Elicits Translation in Large Language Modelscited by 16
  8. 2021On the Evaluation of Machine Translation for Terminology Consistencycited by 15
  9. 2021Continuous Learning in Neural Machine Translation using Bilingual Dictionariescited by 11
  10. 2021Is "moby dick" a Whale or a Bird? Named Entities and Terminology in Speech Translationcited by 11
  11. 2021Encouraging Neural Machine Translation to Satisfy Terminology Constraintscited by 10
  12. 2024Fairness Definitions in Language Models Explainedcited by 10
  13. 2022Integrating Vectorized Lexical Constraints for Neural Machine Translationcited by 9
  14. 2023Terminology-Aware Translation with Constrained Decoding and Large Language Model Promptingcited by 8
  15. 2024Cultural Adaptation of Menus: A Fine-Grained Approachcited by 8
  16. 2021GWLAN: General Word-Level AutocompletioN for Computer-Aided Translationcited by 7
  17. 2022Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Promptscited by 7
  18. 2023Toward Unified Controllable Text Generation via Regular Expression Instructioncited by 7
  19. 2024Efficient Terminology Integration for LLM-based Translation in Specialized Domainscited by 7
  20. 2021End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languagescited by 6
  21. 2022DICTDIS: Dictionary Constrained Disambiguation for Improved NMTcited by 4
  22. 2024Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Modelscited by 4
  23. 2025Specification-Aware Machine Translation and Evaluation for Purpose Alignmentcited by 4
  24. 2021Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Predictioncited by 3
  25. 2021Rule-based Morphological Inflection Improves Neural Terminology Translationcited by 3
  26. 2022Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraintscited by 3
  27. 2023Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraintscited by 3
  28. 2023To be or not to be? an exploration of continuously controllable prompt engineeringcited by 3
  29. 2024Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approachcited by 3
  30. 2025Low-resource Machine Translation for Code-switched Kazakh-Russian Language Paircited by 3
  31. 2025Locate-and-Focus: Enhancing Terminology Translation in Speech Language Modelscited by 3
  32. 2021Machine Translation Customization via Automatic Training Data Selection from the Webcited by 2
  33. 2021CUNI systems for WMT21: Terminology translation Shared Taskcited by 2
  34. 2021Lingua Custodia's participation at the WMT 2021 Machine Translation using Terminologies shared taskcited by 2
  35. 2023Extract and Attend: Improving Entity Translation in Neural Machine Translationcited by 2
  36. 2024Improving Rare Word Translation With Dictionaries and Attention Maskingcited by 2
  37. 2021Modeling Target-side Inflection in Placeholder Translationcited by 1
  38. 2022Accurate Online Posterior Alignments for Principled Lexically-Constrained Decodingcited by 1

50 most cited of 73 All 73 (JSON)