Democratizing Neural Machine Translation with OPUS-MT

2022/12/04 by Jörg Tiedemann, Tiedemann, Jörg, Mikko Aulamo +17 · 19 citations
Computer Science · #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2212.01936

Abstract

This paper presents the OPUS ecosystem with a focus on the development of open machine translation models and tools, and their integration into end-user applications, development platforms and professional workflows. We discuss our on-going mission of increasing language coverage and translation quality, and also describe on-going work on the development of modular translation models and speed-optimized compact solutions for real-time translation on regular desktops and small devices.

Cited by

• Asynchronous Pipeline Parallelism for Real-Time Multilingual Lip Synchronization in Video Communication Systems
• Fluent Alignment with Disfluent Judges: Post-training for Lower-resource Languages
• MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking
• Boosting Medical Vision-Language Pretraining via Momentum Self-Distillation under Limited Computing Resources
• Translation Entropy: A Statistical Framework for Evaluating Translation Systems
• How to Evaluate Speech Translation with Source-Aware Neural MT Metrics
• HPLT 3.0: Very Large-Scale Multilingual Resources for LLMs and MT. Mono- and Bi-lingual Data, Multilingual Evaluation, and Pre-Trained Models
• Style Attack Disguise: When Fonts Become a Camouflage for Adversarial Intent
• Semantic Prosody in Machine Translation: the English-Chinese Case of Passive Structures
• On-device System of Compositional Multi-tasking in Large Language Models
• Improving Mental Health Screening and Early Risk Detection in Spanish
• Scaling, Simplification, and Adaptation: Lessons from Pretraining on Machine-Translated Text
• Cognitive Linguistic Identity Fusion Score (CLIFS): A Scalable Cognition-Informed Approach to Quantifying Identity Fusion from Text
• You Are What You Train: Effects of Data Composition on Training Context-aware Machine Translation Models
• Integrating gender inclusivity into large language models via instruction tuning
• Two Birds with One Stone: Multi-Task Detection and Attribution of LLM-Generated Text
• Neural Machine Translation for Coptic-French: Strategies for Low-Resource Ancient Languages
• Practical, Generalizable and Robust Backdoor Attacks on Text-to-Image Diffusion Models
• Uncovering Cross-Linguistic Disparities in LLMs using Sparse Autoencoders

Related

• OpusCleaner and OpusTrainer, open source toolkits for training Machine Translation and Large language models
• SYSTRAN's Pure Neural Machine Translation Systems
• Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions
• Neural Machine Translation: Challenges, Progress and Future
• Neural Machine Translation: A Review and Survey