Abui Wordnet: Using a Toolbox Dictionary to develop a wordnet for a low-resource language
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989592%3A15210%2F22%3A73618984" target="_blank" >RIV/61989592:15210/22:73618984 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2022.fieldmatters-1.7/" target="_blank" >https://aclanthology.org/2022.fieldmatters-1.7/</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Abui Wordnet: Using a Toolbox Dictionary to develop a wordnet for a low-resource language
Original language description
This paper describes a procedure to link a Toolbox dictionary of a low-resource language to correct synsets, generating a new wordnet. We introduce a bootstrapping technique utilising the information in the gloss fields (English, national, and regional) to generate sense candidates using a naive algorithm based on multilingual sense intersection. We show that this technique is quite effective when glosses are available in more than one language. Our technique complements the previous work by Rosman et al. (2014) which linked the SIL Semantic Domains to wordnet senses. Through this work we have created a small, fully hand-checked wordnet for Abui, containing over 1,400 concepts and 3,600 senses.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
60203 - Linguistics
Result continuities
Project
<a href="/en/project/GA20-18407S" target="_blank" >GA20-18407S: Verb Class Analysis Accelerator for Low-Resource Languages - RoboCorp</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of 1st Workshop on NLP applications to field linguistics
ISBN
—
ISSN
2951-2093
e-ISSN
—
Number of pages
10
Pages from-to
54-63
Publisher name
COLING: International Conference on Computational Linguistics
Place of publication
Gyeongju
Event location
Gyeongju
Event date
Oct 16, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—