It Takes Two: A Dual Stage Approach for Terminology-Aware Translation
This paper introduces DuTerm, a novel two-stage architecture for terminology-constrained machine translation. Our system combines a terminology-aware NMT model, adapted via fine-tuning on large-scale synthetic data, with a prompt-based LLM for post-editing. The LLM stage refines NMT output and enforces terminology adherence. We evaluate DuTerm on English-to German, English-to-Spanish, and English-to-Russian with the WMT 2025 Terminology Shared Task corpus. We demonstrate that flexible, context-driven terminology handling by the LLM consistently yields higher quality translations than strict constraint enforcement. Our results highlight a critical trade-off, revealing that an LLM's work best for high-quality translation as context-driven mutators rather than generators.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationSimilar Papers 제목 키워드 기반
Terminology-Aware Translation with Constrained Decoding and Large Language Model Prompting
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 2…
Language ModelingLanguage ModellingLarge Language ModelMachine Translation+2Improving NMT Quality Using Terminology Injection
Many organizations use domain- or organization-specific words and phrases. This paper explores the use of vetted terminology as an input to neural machine translation (NMT) for improved results: ensuring that the transla…
Machine TranslationNMTTranslationTerminology-Aware Segmentation and Domain Feature for the WMT19 Biomedical Translation Task
In this work, we give a description of the TALP-UPC systems submitted for the WMT19 Biomedical Translation Task. Our proposed strategy is NMT model-independent and relies only on one ingredient, a biomedical terminology …
NMTTranslationTowards Terminology Management Automation for Arabic
This paper presents a method and supporting tools for automation of terminology management for Arabic. The tools extract lists of parallel terminology matching terms in foreign languages to their Arabic counterparts from…
ManagementQuality-aware skill translation models for expert finding on StackOverflow
StackOverflow has become an emerging resource for talent recognition in recent years. While users exploit technical language on StackOverflow, recruiters try to find the relevant candidates for jobs using their own termi…
Translation