Quality Estimation based Feedback Training for Improving Pronoun Translation
Preprint
Abstract
Pronoun translation is a longstanding challenge in neural machine translation (NMT), often requiring inter-sentential context to ensure linguistic accuracy. To address this, we introduce ProNMT, a novel framework designed to enhance pronoun and overall translation quality in context-aware machine translation systems. ProNMT leverages Quality Estimation (QE) models and a unique Pronoun Generation Likelihood-Based Feedback mechanism to iteratively fine-tune pre-trained NMT models without relying on extensive human annotations. The framework combines QE scores with pronoun-specific rewards to guide training, ensuring improved handling of linguistic nuances. Extensive experiments demonstrate significant gains in pronoun translation accuracy and general translation quality across multiple metrics. ProNMT offers an efficient, scalable, and context-aware approach to improving NMT systems, particularly in translating context-dependent elements like pronouns.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model2024
- Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation2020
- Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation2019
- A Large-Scale Test Set for the Evaluation of Context-Aware Pronoun Translation in Neural Machine Translation2018
- Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning2018
- Can Neural Machine Translation be Improved with User Feedback?2018