@inproceedings{waldendorf-etal-2022-improving,
title = "Improving Translation of Out Of Vocabulary Words using Bilingual Lexicon Induction in Low-Resource Machine Translation",
author = "Waldendorf, Jonas and
Birch, Alexandra and
Hadow, Barry and
Micele Barone, Antonio Valerio",
editor = "Duh, Kevin and
Guzm{\'a}n, Francisco",
booktitle = "Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)",
month = sep,
year = "2022",
address = "Orlando, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2022.amta-research.11",
pages = "144--156",
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-{\textgreater}Ps model, compared to a baseline and when combined with back-translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="waldendorf-etal-2022-improving">
<titleInfo>
<title>Improving Translation of Out Of Vocabulary Words using Bilingual Lexicon Induction in Low-Resource Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Waldendorf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Hadow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Valerio</namePart>
<namePart type="family">Micele Barone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Guzmán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Orlando, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">waldendorf-etal-2022-improving</identifier>
<location>
<url>https://aclanthology.org/2022.amta-research.11</url>
</location>
<part>
<date>2022-09</date>
<extent unit="page">
<start>144</start>
<end>156</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Translation of Out Of Vocabulary Words using Bilingual Lexicon Induction in Low-Resource Machine Translation
%A Waldendorf, Jonas
%A Birch, Alexandra
%A Hadow, Barry
%A Micele Barone, Antonio Valerio
%Y Duh, Kevin
%Y Guzmán, Francisco
%S Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)
%D 2022
%8 September
%I Association for Machine Translation in the Americas
%C Orlando, USA
%F waldendorf-etal-2022-improving
%X 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.
%U https://aclanthology.org/2022.amta-research.11
%P 144-156
Markdown (Informal)
[Improving Translation of Out Of Vocabulary Words using Bilingual Lexicon Induction in Low-Resource Machine Translation](https://aclanthology.org/2022.amta-research.11) (Waldendorf et al., AMTA 2022)
ACL