@inproceedings{beermann-etal-2020-developing,
title = "Developing a {T}wi ({A}sante) Dictionary from {A}kan Interlinear Glossed Texts",
author = "Beermann, Dorothee and
Hellan, Lars and
Mihaylov, Pavel and
Struck, Anna",
editor = "Beermann, Dorothee and
Besacier, Laurent and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources association",
url = "https://aclanthology.org/2020.sltu-1.41/",
pages = "294--297",
language = "eng",
ISBN = "979-10-95546-35-1",
abstract = "Traditionally, a lexicographer identifies the lexical items to be added to a dictionary. Here we present a corpus-based approach to dictionary compilation and describe a procedure that derives a Twi dictionary from a TypeCraft corpus of Interlinear Glossed Texts. We first extracted a list of unique words. We excluded words belonging to different dialects of Akan (mostly Fante and Abron). We corrected misspellings and distinguished English loan words to be integrated in our dictionary from instances of code switching. Next to the dictionary itself, one other resource arising from our work is a lexicographical model for Akan which represents the lexical resource itself, and the extended morphological and word class inventories that provide information to be aggregated. We also represent external resources such as the corpus that serves as the source and word level audio files. The Twi dictionary consists at present of 1367 words; it will be available online and from an open mobile app."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="beermann-etal-2020-developing">
<titleInfo>
<title>Developing a Twi (Asante) Dictionary from Akan Interlinear Glossed Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dorothee</namePart>
<namePart type="family">Beermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lars</namePart>
<namePart type="family">Hellan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Mihaylov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Struck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dorothee</namePart>
<namePart type="family">Beermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Besacier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">979-10-95546-35-1</identifier>
</relatedItem>
<abstract>Traditionally, a lexicographer identifies the lexical items to be added to a dictionary. Here we present a corpus-based approach to dictionary compilation and describe a procedure that derives a Twi dictionary from a TypeCraft corpus of Interlinear Glossed Texts. We first extracted a list of unique words. We excluded words belonging to different dialects of Akan (mostly Fante and Abron). We corrected misspellings and distinguished English loan words to be integrated in our dictionary from instances of code switching. Next to the dictionary itself, one other resource arising from our work is a lexicographical model for Akan which represents the lexical resource itself, and the extended morphological and word class inventories that provide information to be aggregated. We also represent external resources such as the corpus that serves as the source and word level audio files. The Twi dictionary consists at present of 1367 words; it will be available online and from an open mobile app.</abstract>
<identifier type="citekey">beermann-etal-2020-developing</identifier>
<location>
<url>https://aclanthology.org/2020.sltu-1.41/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>294</start>
<end>297</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing a Twi (Asante) Dictionary from Akan Interlinear Glossed Texts
%A Beermann, Dorothee
%A Hellan, Lars
%A Mihaylov, Pavel
%A Struck, Anna
%Y Beermann, Dorothee
%Y Besacier, Laurent
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)
%D 2020
%8 May
%I European Language Resources association
%C Marseille, France
%@ 979-10-95546-35-1
%G eng
%F beermann-etal-2020-developing
%X Traditionally, a lexicographer identifies the lexical items to be added to a dictionary. Here we present a corpus-based approach to dictionary compilation and describe a procedure that derives a Twi dictionary from a TypeCraft corpus of Interlinear Glossed Texts. We first extracted a list of unique words. We excluded words belonging to different dialects of Akan (mostly Fante and Abron). We corrected misspellings and distinguished English loan words to be integrated in our dictionary from instances of code switching. Next to the dictionary itself, one other resource arising from our work is a lexicographical model for Akan which represents the lexical resource itself, and the extended morphological and word class inventories that provide information to be aggregated. We also represent external resources such as the corpus that serves as the source and word level audio files. The Twi dictionary consists at present of 1367 words; it will be available online and from an open mobile app.
%U https://aclanthology.org/2020.sltu-1.41/
%P 294-297
Markdown (Informal)
[Developing a Twi (Asante) Dictionary from Akan Interlinear Glossed Texts](https://aclanthology.org/2020.sltu-1.41/) (Beermann et al., SLTU 2020)
ACL
- Dorothee Beermann, Lars Hellan, Pavel Mihaylov, and Anna Struck. 2020. Developing a Twi (Asante) Dictionary from Akan Interlinear Glossed Texts. In Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL), pages 294–297, Marseille, France. European Language Resources association.