← Back to papers
2020 AACL AACL 2020

Zero-shot translation among Indian languages

Abstract

AbstractStandard neural machine translation (NMT) allows a model to perform translation between a pair of languages. Multilingual neural machine translation (NMT), on the other hand, allows a model to perform translation between several language pairs, even between language pairs for which no sentences pair has been seen during training (zero-shot translation). This paper presents experiments with zero-shot translation on low resource Indian languages with a very small amount of data for each language pair. We first report results on balanced data over all considered language pairs. We then expand our experiments for additional three rounds by increasing the training data with 2,000 sentence pairs in each round for some of the language pairs. We obtain an increase in translation accuracy with its balanced data settings score multiplied by 7 for Manipuri to Hindi during Round-III of zero-shot translation.

🚀 Conference Pioneer — AACL 2020
🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning and Natural Language Processing
🐣 Hot Topic Early Bird — multilingual neural machine translation
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Security & Privacy, Speech & Audio

Authors

Rudali Huidrom , Yves Lepage

Topics

Machine Learning > Learning Types > Zero-Shot Learning Natural Language Processing > Applications > Machine Translation Natural Language Processing > Resources & Methods > Multilingual NLP Machine Learning > Learning Paradigms > Transfer Learning Deep Learning > Learning Types > Self-Supervised Learning

Keywords

multilingual translation neural machine translation low-resource language indian language multilingual neural machine translation zero-shot translation low resource language
Download PDF

Related papers

Can Monolingual Pretrained Models Help Cross-Lingual Classification? 2020
Text Simplification with Reinforcement Learning Using Supervised Rewards on Grammaticality, Meaning Preservation, and Simplicity 2020
ISA: An Intelligent Shopping Assistant 2020
Social Media Medical Concept Normalization using RoBERTa in Ontology Enriched Text Similarity Framework 2020
Overcoming Resistance: The Normalization of an Amazonian Tribal Language 2020