Improving Translation of Out Of Vocabulary Words using Bilingual Lexicon Induction in Low-Resource Machine Translation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Dictionary-based data augmentation techniques have been used in the field of domain adaptation to learn words that do not appear in the parallel training data of a machine translation model. These techniques strive to learn correct translations of these words by generating a synthetic corpus from in-domain monolingual data utilising a dictionary obtained from bilingual lexicon induction. This paper applies these techniques to low resource machine translation, where there is often a shift in distribution of content between the parallel data and any monolingual data. English-Pashto machine learning systems are trained using a novel approach that introduces monolingual data to existing joint learning techniques for bilingual word embeddings, combined with word-for-word back-translation to improve the translation of words that do not or rarely appear in the parallel training data. Improvements are made both in terms of BLEU, chrF and word translation accuracy for an En-textgreaterPs model, compared to a baseline and when combined with back-translation.
Original languageEnglish
Title of host publicationProceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)
EditorsKevin Duh, Francisco Guzman, Stephen Richardson
Place of PublicationOrlando, USA
PublisherAssociation for Machine Translation in the Americas, AMTA
Pages144-156
Number of pages13
Publication statusPublished - 16 Sep 2022
Event15th Biennial Conference of the Association for Machine Translation in the Americas - Orlando, United States
Duration: 12 Sep 202216 Sep 2022
Conference number: 15
https://amtaweb.org/

Conference

Conference15th Biennial Conference of the Association for Machine Translation in the Americas
Abbreviated titleAMTA 2022
Country/TerritoryUnited States
CityOrlando
Period12/09/2216/09/22
Internet address

Fingerprint

Dive into the research topics of 'Improving Translation of Out Of Vocabulary Words using Bilingual Lexicon Induction in Low-Resource Machine Translation'. Together they form a unique fingerprint.

Cite this