@inproceedings{ngomane-etal-2023-unsupervised,
title = "Unsupervised Cross-lingual Word Embedding Representation for {E}nglish-isi{Z}ulu",
author = "Ngomane, Derwin and
Mabuya, Rooweither and
Abbott, Jade and
Marivate, Vukosi",
editor = "Mabuya, Rooweither and
Mthobela, Don and
Setaka, Mmasibidi and
Van Zaanen, Menno",
booktitle = "Proceedings of the Fourth workshop on Resources for African Indigenous Languages (RAIL 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.rail-1.2",
doi = "10.18653/v1/2023.rail-1.2",
pages = "11--17",
abstract = "In this study, we investigate the effectiveness of using cross-lingual word embeddings for zero-shot transfer learning between a language with an abundant resource, English, and a languagewith limited resource, isiZulu. IsiZulu is a part of the South African Nguni language family, which is characterised by complex agglutinating morphology. We use VecMap, an open source tool, to obtain cross-lingual word embeddings. To perform an extrinsic evaluation of the effectiveness of the embeddings, we train a news classifier on labelled English data in order to categorise unlabelled isiZulu data using zero-shot transfer learning. In our study, we found our model to have a weighted average F1-score of 0.34. Our findings demonstrate that VecMap generates modular word embeddings in the cross-lingual space that have an impact on the downstream classifier used for zero-shot transfer learning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ngomane-etal-2023-unsupervised">
<titleInfo>
<title>Unsupervised Cross-lingual Word Embedding Representation for English-isiZulu</title>
</titleInfo>
<name type="personal">
<namePart type="given">Derwin</namePart>
<namePart type="family">Ngomane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rooweither</namePart>
<namePart type="family">Mabuya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Abbott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vukosi</namePart>
<namePart type="family">Marivate</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth workshop on Resources for African Indigenous Languages (RAIL 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rooweither</namePart>
<namePart type="family">Mabuya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Don</namePart>
<namePart type="family">Mthobela</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mmasibidi</namePart>
<namePart type="family">Setaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Menno</namePart>
<namePart type="family">Van Zaanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this study, we investigate the effectiveness of using cross-lingual word embeddings for zero-shot transfer learning between a language with an abundant resource, English, and a languagewith limited resource, isiZulu. IsiZulu is a part of the South African Nguni language family, which is characterised by complex agglutinating morphology. We use VecMap, an open source tool, to obtain cross-lingual word embeddings. To perform an extrinsic evaluation of the effectiveness of the embeddings, we train a news classifier on labelled English data in order to categorise unlabelled isiZulu data using zero-shot transfer learning. In our study, we found our model to have a weighted average F1-score of 0.34. Our findings demonstrate that VecMap generates modular word embeddings in the cross-lingual space that have an impact on the downstream classifier used for zero-shot transfer learning.</abstract>
<identifier type="citekey">ngomane-etal-2023-unsupervised</identifier>
<identifier type="doi">10.18653/v1/2023.rail-1.2</identifier>
<location>
<url>https://aclanthology.org/2023.rail-1.2</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>11</start>
<end>17</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Cross-lingual Word Embedding Representation for English-isiZulu
%A Ngomane, Derwin
%A Mabuya, Rooweither
%A Abbott, Jade
%A Marivate, Vukosi
%Y Mabuya, Rooweither
%Y Mthobela, Don
%Y Setaka, Mmasibidi
%Y Van Zaanen, Menno
%S Proceedings of the Fourth workshop on Resources for African Indigenous Languages (RAIL 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F ngomane-etal-2023-unsupervised
%X In this study, we investigate the effectiveness of using cross-lingual word embeddings for zero-shot transfer learning between a language with an abundant resource, English, and a languagewith limited resource, isiZulu. IsiZulu is a part of the South African Nguni language family, which is characterised by complex agglutinating morphology. We use VecMap, an open source tool, to obtain cross-lingual word embeddings. To perform an extrinsic evaluation of the effectiveness of the embeddings, we train a news classifier on labelled English data in order to categorise unlabelled isiZulu data using zero-shot transfer learning. In our study, we found our model to have a weighted average F1-score of 0.34. Our findings demonstrate that VecMap generates modular word embeddings in the cross-lingual space that have an impact on the downstream classifier used for zero-shot transfer learning.
%R 10.18653/v1/2023.rail-1.2
%U https://aclanthology.org/2023.rail-1.2
%U https://doi.org/10.18653/v1/2023.rail-1.2
%P 11-17
Markdown (Informal)
[Unsupervised Cross-lingual Word Embedding Representation for English-isiZulu](https://aclanthology.org/2023.rail-1.2) (Ngomane et al., RAIL 2023)
ACL