@inproceedings{mersha-wu-2020-morphology,
title = "Morphology-rich Alphasyllabary Embeddings",
author = "Mersha, Amanuel and
Wu, Stephen",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.315",
pages = "2590--2595",
abstract = "Word embeddings have been successfully trained in many languages. However, both intrinsic and extrinsic metrics are variable across languages, especially for languages that depart significantly from English in morphology and orthography. This study focuses on building a word embedding model suitable for the Semitic language of Amharic (Ethiopia), which is both morphologically rich and written as an alphasyllabary (abugida) rather than an alphabet. We compare embeddings from tailored neural models, simple pre-processing steps, off-the-shelf baselines, and parallel tasks on a better-resourced Semitic language {--} Arabic. Experiments show our model{'}s performance on word analogy tasks, illustrating the divergent objectives of morphological vs. semantic analogies.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mersha-wu-2020-morphology">
<titleInfo>
<title>Morphology-rich Alphasyllabary Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amanuel</namePart>
<namePart type="family">Mersha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Word embeddings have been successfully trained in many languages. However, both intrinsic and extrinsic metrics are variable across languages, especially for languages that depart significantly from English in morphology and orthography. This study focuses on building a word embedding model suitable for the Semitic language of Amharic (Ethiopia), which is both morphologically rich and written as an alphasyllabary (abugida) rather than an alphabet. We compare embeddings from tailored neural models, simple pre-processing steps, off-the-shelf baselines, and parallel tasks on a better-resourced Semitic language – Arabic. Experiments show our model’s performance on word analogy tasks, illustrating the divergent objectives of morphological vs. semantic analogies.</abstract>
<identifier type="citekey">mersha-wu-2020-morphology</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.315</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>2590</start>
<end>2595</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Morphology-rich Alphasyllabary Embeddings
%A Mersha, Amanuel
%A Wu, Stephen
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F mersha-wu-2020-morphology
%X Word embeddings have been successfully trained in many languages. However, both intrinsic and extrinsic metrics are variable across languages, especially for languages that depart significantly from English in morphology and orthography. This study focuses on building a word embedding model suitable for the Semitic language of Amharic (Ethiopia), which is both morphologically rich and written as an alphasyllabary (abugida) rather than an alphabet. We compare embeddings from tailored neural models, simple pre-processing steps, off-the-shelf baselines, and parallel tasks on a better-resourced Semitic language – Arabic. Experiments show our model’s performance on word analogy tasks, illustrating the divergent objectives of morphological vs. semantic analogies.
%U https://aclanthology.org/2020.lrec-1.315
%P 2590-2595
Markdown (Informal)
[Morphology-rich Alphasyllabary Embeddings](https://aclanthology.org/2020.lrec-1.315) (Mersha & Wu, LREC 2020)
ACL
- Amanuel Mersha and Stephen Wu. 2020. Morphology-rich Alphasyllabary Embeddings. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 2590–2595, Marseille, France. European Language Resources Association.