conftrace_

2023 ACL ACL 2023

Few-shot Spanish-Aymara Machine Translation Using English-Aymara Lexicon

Abstract

AbstractThis paper presents the experiments to train a Spanish-Aymara machine translation model for the AmericasNLP 2023 Machine Translation shared task. We included the English-Aymara GlobalVoices corpus and an English-Aymara lexicon to train the model and limit our training resources to train the model in a \textit{few-shot} manner.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

🐣 Hot Topic Early Bird - low-resource language

Authors

Nat Gillin, Brian Gummibaerhausen

Topics

Natural Language Processing > Applications > Machine Translation Machine Learning > Learning Types > Few-Shot Learning Machine Learning > Learning Types > Transfer Learning Deep Learning > Learning Types > Few-Shot Learning

Keywords

few-shot learning transfer learning machine translation low-resource language multilingual neural machine translation

More from ACL 2023

All ACL 2023 papers →

Finding words that aren’t there: Using word embeddings to improve dictionary search for low-resource languages

Enhancing Spanish-Quechua Machine Translation with Pre-Trained Models and Diverse Data Sources: LCT-EHU at AmericasNLP Shared Task

ChatGPT is not a good indigenous translator

PlayGround Low Resource Machine Translation System for the 2023 AmericasNLP Shared Task

Four Approaches to Low-Resource Multilingual NMT: The Helsinki Submission to the AmericasNLP 2023 Shared Task

Sheffield’s Submission to the AmericasNLP Shared Task on Machine Translation into Indigenous Languages