Tigrinya Neural Machine Translation with Transfer Learning for Humanitarian Response

2020/03/09 by Alp Öktem, Öktem, Alp, Mirko Plitt +3 · 3 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2003.11523

openalex publication_date 2020/03/09 · openalex created_date 2020/04/03 · openalex updated_date 2026/07/28

Abstract

We report our experiments in building a domain-specific Tigrinya-to-English neural machine translation system. We use transfer learning from other Ge'ez script languages and report an improvement of 1.3 BLEU points over a classic neural baseline. We publish our development pipeline as an open-source library and also provide a demonstration application.

Cited by

• Low-Resource English-Tigrinya MT: Leveraging Multilingual Models, Custom Tokenizers, and Clean Evaluation Benchmarks
• Natural Language Processing for Tigrinya: Current State and Future Directions
• A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings

Related

• Low-Resource English-Tigrinya MT: Leveraging Multilingual Models, Custom Tokenizers, and Clean Evaluation Benchmarks
• An Exploration of Data Augmentation Techniques for Improving English to Tigrinya Translation
• Natural Language Processing for Tigrinya: Current State and Future Directions
• Low-Resource Neural Machine Translation Using Recurrent Neural Networks and Transfer Learning: A Case Study on English-to-Igbo
• Low Resource Neural Machine Translation: A Benchmark for Five African Languages