# Terminology-Aware Translation with Constrained Decoding and Large Language Model Prompting

arXiv: https://arxiv.org/abs/2310.05824 · HTML: https://mlsanity.com/paper/2310.05824/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 9 Oct 2023.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Prompting Large Language Model for Machine Translation: A Case Study](https://mlsanity.com/paper/2301.07069/) (2023)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Marian: Fast Neural Machine Translation in C++](https://mlsanity.com/paper/1804.00344/) (2018)
- [Word Alignment by Fine-tuning Embeddings on Parallel Corpora](https://mlsanity.com/paper/2101.08231/) (2021)
- [Prompting PaLM for Translation: Assessing Strategies and Performance](https://mlsanity.com/paper/2211.09102/) (2022)
- [Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation](https://mlsanity.com/paper/2302.07856/) (2023)
- [Training Neural Machine Translation To Apply Terminology Constraints](https://mlsanity.com/paper/1906.01105/) (2019)
- [Adaptive Machine Translation with Large Language Models](https://mlsanity.com/paper/2301.13294/) (2023)
- [Neural Machine Translation Decoding with Terminology Constraints](https://mlsanity.com/paper/1805.03750/) (2018)
- [Iterative Translation Refinement with Large Language Models](https://mlsanity.com/paper/2306.03856/) (2023)
- [Facilitating Terminology Translation with Target Lemma Annotations](https://mlsanity.com/paper/2101.10035/) (2021)
- [CUNI systems for WMT21: Terminology translation Shared Task](https://mlsanity.com/paper/2109.09350/) (2021)

## Built on by (most cited first, 8 of 8)

- [ElecBench: a Power Dispatch Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2407.05365/) (2024)
- [Efficient Terminology Integration for LLM-based Translation in Specialized Domains](https://mlsanity.com/paper/2410.15690/) (2024)
- [TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word Alignment](https://mlsanity.com/paper/2505.21172/) (2025)
- [Locate-and-Focus: Enhancing Terminology Translation in Speech Language Models](https://mlsanity.com/paper/2507.18263/) (2025)
- [Translate-and-Revise: Boosting Large Language Models for Constrained Translation](https://mlsanity.com/paper/2407.13164/) (2024)
- [Translation Asymmetry in LLMs as a Data Augmentation Factor: A Case Study for 6 Romansh Language Varieties](https://mlsanity.com/paper/2603.25489/) (2026)
- [OpusCleaner and OpusTrainer, open source toolkits for training Machine Translation and Large language models](https://mlsanity.com/paper/2311.14838/) (2023)
- [Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)](https://mlsanity.com/paper/2412.18367/) (2024)

## Abstract (arXiv)

Terminology correctness is important in the downstream application of machine translation, and a prevalent way to ensure this is to inject terminology constraints into a translation system. In our submission to the WMT 2023 terminology translation task, we adopt a translate-then-refine approach which can be domain-independent and requires minimal manual efforts. We annotate random source words with pseudo-terminology translations obtained from word alignment to first train a terminology-aware model. Further, we explore two post-processing methods. First, we use an alignment process to discover whether a terminology constraint has been violated, and if so, we re-decode with the violating word negatively constrained. Alternatively, we leverage a large language model to refine a hypothesis by providing it with terminology constraints. Results show that our terminology-aware model learns to incorporate terminologies effectively, and the large language model refinement process can further improve terminology recall.