Prompt-Driven Neural Machine Translation
Neural machine translation (NMT) has obtained significant performance improvement over the recent years. However, NMT models still face various challenges including fragility and lack of style flexibility. Moreover, current methods for instance-level constraints are limited in that they are either constraint-specific or model-specific. To this end, we propose prompt-driven neural machine translation to incorporate prompts for enhancing translation control and enriching flexibility. Empirical results demonstrate the effectiveness of our method in both prompt responding and translation quality. Through human evaluation, we further show the flexibility of prompt control and the efficiency in human-in-the-loop translation.
Code (1)
Tasks
Machine TranslationNMTTranslationSimilar Papers 제목 키워드 기반
Data-Driven Approach for Formality-Sensitive Machine Translation: Language-Specific Handling and Synthetic Data Generation
In this paper, we introduce a data-driven approach for Formality-Sensitive Machine Translation (FSMT) that caters to the unique linguistic properties of four target languages. Our methodology centers on two core strategi…
Machine TranslationPrompt EngineeringSynthetic Data GenerationTranslationPOMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation
Low-resource languages (LRLs) face challenges in supervised neural machine translation due to limited parallel data, prompting research into unsupervised methods. Unsupervised neural machine translation (UNMT) methods, i…
In-Context LearningMachine TranslationNMTTransfer Learning+1The Role of Prompt Language and Translation-Theory-Driven Prompts in Large Language Models: A Case Study on Spanish-Chinese Journalistic Translation
This study examines how prompt language and translation theory-driven prompt design influence the quality of Spanish-Chinese journalistic translations generated by GPT-5.2. A parallel corpus of four editorials from El Pa…
Reflective Translation: Improving Low-Resource Machine Translation via Structured Self-Reflection
Low-resource languages such as isiZulu and isiXhosa face persistent challenges in machine translation due to limited parallel data and linguistic resources. Recent advances in large language models suggest that self-refl…
Machine TranslationIt 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…
Machine Translation