Neural Machine Translation Decoding with Terminology Constraints
Not on the map. Why?
Abstract (arXiv)
Despite the impressive quality improvements yielded by neural machine translation (NMT) systems, controlling their translation output to adhere to user-provided terminology constraints remains an open problem. We describe our approach to constrained neural decoding based on finite-state machines and multi-stack decoding which supports target-side constraints as well as constraints with corresponding aligned input text spans. We demonstrate the performance of our framework on multiple translation tasks and motivate the need for constrained decoding with attentions as a means of reducing misplacement and duplication when translating user constraints.
Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 May 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 16; 2022: 7; 2023: 7; 2024: 4; 2025: 2.
36 papers.
Sort:
- 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 153
- 2023COLLIE: Systematic Construction of Constrained Text Generation Taskscited by 69
- 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 51
- 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
- 2021Controlling Conditional Language Models without Catastrophic Forgettingcited by 32
- 2022General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretrainingcited by 25
- 2021Facilitating Terminology Translation with Target Lemma Annotationscited by 19
- 2023Domain Terminology Integration into Machine Translation: Leveraging Large Language Modelscited by 17
- 2021Continuous Learning in Neural Machine Translation using Bilingual Dictionariescited by 11
- 2021Is "moby dick" a Whale or a Bird? Named Entities and Terminology in Speech Translationcited by 11
- 2021Encouraging Neural Machine Translation to Satisfy Terminology Constraintscited by 10
- 2022Integrating Vectorized Lexical Constraints for Neural Machine Translationcited by 9
24 more
- 2021WeTS: A Benchmark for Translation Suggestioncited by 8
- 2023Multilingual Sentence Transformer as A Multilingual Word Alignercited by 8
- 2023Terminology-Aware Translation with Constrained Decoding and Large Language Model Promptingcited by 8
- 2021GWLAN: General Word-Level AutocompletioN for Computer-Aided Translationcited by 7
- 2021Controlling Text Edition by Changing Answers of Specific Questionscited by 6
- 2021Constraining Linear-chain CRFs to Regular Languagescited by 6
- 2021End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languagescited by 6
- 2021Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Predictioncited by 3
- 2023Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraintscited by 3
- 2024Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approachcited by 3
- 2025Locate-and-Focus: Enhancing Terminology Translation in Speech Language Modelscited by 3
- 2021CUNI systems for WMT21: Terminology translation Shared Taskcited by 2
- 2022Accurate Online Posterior Alignments for Principled Lexically-Constrained Decodingcited by 1
- 2023Disambiguated Lexically Constrained Neural Machine Translationcited by 1
- 2023Negative Lexical Constraints in Neural Machine Translationcited by 1
- 2024On Translating Technical Terminology: A Translation Workflow for Machine-Translated Acronymscited by 1
- 2024Efficient Technical Term Translation: A Knowledge Distillation Approach for Parenthetical Terminology Translationcited by 1
- 2024Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)cited by 1
- 2021Bilingual Terminology Extraction from Comparable E-Commerce Corporacited by 0
- 2022A Template-based Method for Constrained Neural Machine Translationcited by 0
- 2022Open Terminology Management and Sharing Toolkit for Federation of Terminology Databasescited by 0
- 2022The University of Edinburgh's Submission to the WMT22 Code-Mixing Shared Task (MixMT)cited by 0
- 2022Third-Party Aligner for Neural Word Alignmentscited by 0
- 2025Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text Systemcited by 0
- 2025Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System26 Aug 2025
- 2025Locate-and-Focus: Enhancing Terminology Translation in Speech Language Models24 Jul 2025
- 2024Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)24 Dec 2024
- 2024Efficient Technical Term Translation: A Knowledge Distillation Approach for Parenthetical Terminology Translation1 Oct 2024
- 2024On Translating Technical Terminology: A Translation Workflow for Machine-Translated Acronyms26 Sep 2024
- 2024Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach13 Sep 2024
- 2023Domain Terminology Integration into Machine Translation: Leveraging Large Language Models22 Oct 2023
- 2023Terminology-Aware Translation with Constrained Decoding and Large Language Model Prompting9 Oct 2023
- 2023Negative Lexical Constraints in Neural Machine Translation7 Aug 2023
- 2023COLLIE: Systematic Construction of Constrained Text Generation Tasks17 Jul 2023
- 2023Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints21 Jun 2023
- 2023Disambiguated Lexically Constrained Neural Machine Translation27 May 2023
24 more
- 2023Multilingual Sentence Transformer as A Multilingual Word Aligner28 Jan 2023
- 2022Third-Party Aligner for Neural Word Alignments8 Nov 2022
- 2022The University of Edinburgh's Submission to the WMT22 Code-Mixing Shared Task (MixMT)20 Oct 2022
- 2022Open Terminology Management and Sharing Toolkit for Federation of Terminology Databases14 Jul 2022
- 2022A Template-based Method for Constrained Neural Machine Translation23 May 2022
- 2022Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding2 Apr 2022
- 2022Integrating Vectorized Lexical Constraints for Neural Machine Translation23 Mar 2022
- 2022General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretraining21 Mar 2022
- 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics16 Dec 2021
- 2021Controlling Conditional Language Models without Catastrophic Forgetting1 Dec 2021
- 2021WeTS: A Benchmark for Translation Suggestion11 Oct 2021
- 2021CUNI systems for WMT21: Terminology translation Shared Task20 Sep 2021
- 2021Is "moby dick" a Whale or a Bird? Named Entities and Terminology in Speech Translation15 Sep 2021
- 2021End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages23 Jun 2021
- 2021Constraining Linear-chain CRFs to Regular Languages14 Jun 2021
- 2021Encouraging Neural Machine Translation to Satisfy Terminology Constraints7 Jun 2021
- 2021GWLAN: General Word-Level AutocompletioN for Computer-Aided Translation31 May 2021
- 2021Controlling Text Edition by Changing Answers of Specific Questions23 May 2021
- 2021Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction12 May 2021
- 2021Bilingual Terminology Extraction from Comparable E-Commerce Corpora15 Apr 2021
- 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey14 Apr 2021
- 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfer8 Apr 2021
- 2021Continuous Learning in Neural Machine Translation using Bilingual Dictionaries12 Feb 2021
- 2021Facilitating Terminology Translation with Target Lemma Annotations25 Jan 2021
- 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 153
- 2023COLLIE: Systematic Construction of Constrained Text Generation Taskscited by 69
- 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 51
- 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
- 2021Controlling Conditional Language Models without Catastrophic Forgettingcited by 32
- 2022General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretrainingcited by 25
- 2021Facilitating Terminology Translation with Target Lemma Annotationscited by 19
- 2023Domain Terminology Integration into Machine Translation: Leveraging Large Language Modelscited by 17
- 2021Continuous Learning in Neural Machine Translation using Bilingual Dictionariescited by 11
- 2021Is "moby dick" a Whale or a Bird? Named Entities and Terminology in Speech Translationcited by 11
- 2021Encouraging Neural Machine Translation to Satisfy Terminology Constraintscited by 10
- 2022Integrating Vectorized Lexical Constraints for Neural Machine Translationcited by 9
12 most cited of 36 All 36 (JSON)
- 2025Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System26 Aug 2025
- 2025Locate-and-Focus: Enhancing Terminology Translation in Speech Language Models24 Jul 2025
- 2024Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)24 Dec 2024
- 2024Efficient Technical Term Translation: A Knowledge Distillation Approach for Parenthetical Terminology Translation1 Oct 2024
- 2024On Translating Technical Terminology: A Translation Workflow for Machine-Translated Acronyms26 Sep 2024
- 2024Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach13 Sep 2024
- 2023Domain Terminology Integration into Machine Translation: Leveraging Large Language Models22 Oct 2023
- 2023Terminology-Aware Translation with Constrained Decoding and Large Language Model Prompting9 Oct 2023
- 2023Negative Lexical Constraints in Neural Machine Translation7 Aug 2023
- 2023COLLIE: Systematic Construction of Constrained Text Generation Tasks17 Jul 2023
- 2023Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints21 Jun 2023
- 2023Disambiguated Lexically Constrained Neural Machine Translation27 May 2023
12 newest of 36 All 36 (JSON)