@inproceedings{maurya-etal-2024-charspan,
title = "{C}har{S}pan: Utilizing Lexical Similarity to Enable Zero-Shot Machine Translation for Extremely Low-resource Languages",
author = "Maurya, Kaushal and
Kejriwal, Rahul and
Desarkar, Maunendra and
Kunchukuttan, Anoop",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-short.26",
pages = "294--310",
abstract = "We address the task of machine translation (MT) from extremely low-resource language (ELRL) to English by leveraging cross-lingual transfer from *closely-related* high-resource language (HRL). The development of an MT system for ELRL is challenging because these languages typically lack parallel corpora and monolingual corpora, and their representations are absent from large multilingual language models. Many ELRLs share lexical similarities with some HRLs, which presents a novel modeling opportunity. However, existing subword-based neural MT models do not explicitly harness this lexical similarity, as they only implicitly align HRL and ELRL latent embedding space. To overcome this limitation, we propose a novel, CharSpan, approach based on character-span noise augmentation into the training data of HRL. This serves as a regularization technique, making the model more robust to \textit{lexical divergences} between the HRL and ELRL, thus facilitating effective cross-lingual transfer. Our method significantly outperformed strong baselines in zero-shot settings on closely related HRL and ELRL pairs from three diverse language families, emerging as the state-of-the-art model for ELRLs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maurya-etal-2024-charspan">
<titleInfo>
<title>CharSpan: Utilizing Lexical Similarity to Enable Zero-Shot Machine Translation for Extremely Low-resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kaushal</namePart>
<namePart type="family">Maurya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Kejriwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maunendra</namePart>
<namePart type="family">Desarkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kunchukuttan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We address the task of machine translation (MT) from extremely low-resource language (ELRL) to English by leveraging cross-lingual transfer from *closely-related* high-resource language (HRL). The development of an MT system for ELRL is challenging because these languages typically lack parallel corpora and monolingual corpora, and their representations are absent from large multilingual language models. Many ELRLs share lexical similarities with some HRLs, which presents a novel modeling opportunity. However, existing subword-based neural MT models do not explicitly harness this lexical similarity, as they only implicitly align HRL and ELRL latent embedding space. To overcome this limitation, we propose a novel, CharSpan, approach based on character-span noise augmentation into the training data of HRL. This serves as a regularization technique, making the model more robust to lexical divergences between the HRL and ELRL, thus facilitating effective cross-lingual transfer. Our method significantly outperformed strong baselines in zero-shot settings on closely related HRL and ELRL pairs from three diverse language families, emerging as the state-of-the-art model for ELRLs.</abstract>
<identifier type="citekey">maurya-etal-2024-charspan</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-short.26</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>294</start>
<end>310</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CharSpan: Utilizing Lexical Similarity to Enable Zero-Shot Machine Translation for Extremely Low-resource Languages
%A Maurya, Kaushal
%A Kejriwal, Rahul
%A Desarkar, Maunendra
%A Kunchukuttan, Anoop
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F maurya-etal-2024-charspan
%X We address the task of machine translation (MT) from extremely low-resource language (ELRL) to English by leveraging cross-lingual transfer from *closely-related* high-resource language (HRL). The development of an MT system for ELRL is challenging because these languages typically lack parallel corpora and monolingual corpora, and their representations are absent from large multilingual language models. Many ELRLs share lexical similarities with some HRLs, which presents a novel modeling opportunity. However, existing subword-based neural MT models do not explicitly harness this lexical similarity, as they only implicitly align HRL and ELRL latent embedding space. To overcome this limitation, we propose a novel, CharSpan, approach based on character-span noise augmentation into the training data of HRL. This serves as a regularization technique, making the model more robust to lexical divergences between the HRL and ELRL, thus facilitating effective cross-lingual transfer. Our method significantly outperformed strong baselines in zero-shot settings on closely related HRL and ELRL pairs from three diverse language families, emerging as the state-of-the-art model for ELRLs.
%U https://aclanthology.org/2024.eacl-short.26
%P 294-310
Markdown (Informal)
[CharSpan: Utilizing Lexical Similarity to Enable Zero-Shot Machine Translation for Extremely Low-resource Languages](https://aclanthology.org/2024.eacl-short.26) (Maurya et al., EACL 2024)
ACL