@inproceedings{chimoto-bassett-2022-low,
title = "Very Low Resource Sentence Alignment: Luhya and {S}wahili",
author = "Chimoto, Everlyn and
Bassett, Bruce",
booktitle = "Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022)",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.loresmt-1.1",
pages = "1--8",
abstract = "Language-agnostic sentence embeddings generated by pre-trained models such as LASER and LaBSE are attractive options for mining large datasets to produce parallel corpora for low-resource machine translation. We test LASER and LaBSE in extracting bitext for two related low-resource African languages: Luhya and Swahili. For this work, we created a new parallel set of nearly 8000 Luhya-English sentences which allows a new zero-shot test of LASER and LaBSE. We find that LaBSE significantly outperforms LASER on both languages. Both LASER and LaBSE however perform poorly at zero-shot alignment on Luhya, achieving just 1.5{\%} and 22.0{\%} successful alignments respectively (P@1 score). We fine-tune the embeddings on a small set of parallel Luhya sentences and show significant gains, improving the LaBSE alignment accuracy to 53.3{\%}. Further, restricting the dataset to sentence embedding pairs with cosine similarity above 0.7 yielded alignments with over 85{\%} accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chimoto-bassett-2022-low">
<titleInfo>
<title>Very Low Resource Sentence Alignment: Luhya and Swahili</title>
</titleInfo>
<name type="personal">
<namePart type="given">Everlyn</namePart>
<namePart type="family">Chimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruce</namePart>
<namePart type="family">Bassett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language-agnostic sentence embeddings generated by pre-trained models such as LASER and LaBSE are attractive options for mining large datasets to produce parallel corpora for low-resource machine translation. We test LASER and LaBSE in extracting bitext for two related low-resource African languages: Luhya and Swahili. For this work, we created a new parallel set of nearly 8000 Luhya-English sentences which allows a new zero-shot test of LASER and LaBSE. We find that LaBSE significantly outperforms LASER on both languages. Both LASER and LaBSE however perform poorly at zero-shot alignment on Luhya, achieving just 1.5% and 22.0% successful alignments respectively (P@1 score). We fine-tune the embeddings on a small set of parallel Luhya sentences and show significant gains, improving the LaBSE alignment accuracy to 53.3%. Further, restricting the dataset to sentence embedding pairs with cosine similarity above 0.7 yielded alignments with over 85% accuracy.</abstract>
<identifier type="citekey">chimoto-bassett-2022-low</identifier>
<location>
<url>https://aclanthology.org/2022.loresmt-1.1</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>1</start>
<end>8</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Very Low Resource Sentence Alignment: Luhya and Swahili
%A Chimoto, Everlyn
%A Bassett, Bruce
%S Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022)
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F chimoto-bassett-2022-low
%X Language-agnostic sentence embeddings generated by pre-trained models such as LASER and LaBSE are attractive options for mining large datasets to produce parallel corpora for low-resource machine translation. We test LASER and LaBSE in extracting bitext for two related low-resource African languages: Luhya and Swahili. For this work, we created a new parallel set of nearly 8000 Luhya-English sentences which allows a new zero-shot test of LASER and LaBSE. We find that LaBSE significantly outperforms LASER on both languages. Both LASER and LaBSE however perform poorly at zero-shot alignment on Luhya, achieving just 1.5% and 22.0% successful alignments respectively (P@1 score). We fine-tune the embeddings on a small set of parallel Luhya sentences and show significant gains, improving the LaBSE alignment accuracy to 53.3%. Further, restricting the dataset to sentence embedding pairs with cosine similarity above 0.7 yielded alignments with over 85% accuracy.
%U https://aclanthology.org/2022.loresmt-1.1
%P 1-8
Markdown (Informal)
[Very Low Resource Sentence Alignment: Luhya and Swahili](https://aclanthology.org/2022.loresmt-1.1) (Chimoto & Bassett, LoResMT 2022)
ACL
- Everlyn Chimoto and Bruce Bassett. 2022. Very Low Resource Sentence Alignment: Luhya and Swahili. In Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022), pages 1–8, Gyeongju, Republic of Korea. Association for Computational Linguistics.