A Free/Open-Source Morphological Analyser and Generator for Sakha

We present, to our knowledge, the first ever published morphological analyser and generator for Sakha, a marginalised language of Siberia. The transducer, developed using HFST, has coverage of solidly above 90%, and high precision. In the development of the analyser, we have expanded linguistic know...

Full description

Bibliographic Details
Main Authors: Ivanova, Sardana, Washington, Jonathan, Tyers, Francis M.
Other Authors: Department of Computer Science
Format: Conference Object
Language:English
Published: 2022
Subjects:
113 Computer and information sciences
Sakha
Siberia
Online Access:http://hdl.handle.net/10138/347045
id ftunivhelsihelda:oai:helda.helsinki.fi:10138/347045
record_format openpolar
spelling ftunivhelsihelda:oai:helda.helsinki.fi:10138/347045 2024-01-07T09:46:19+01:00 A Free/Open-Source Morphological Analyser and Generator for Sakha Ivanova, Sardana Washington, Jonathan Tyers, Francis M. Department of Computer Science 2022-08-17T04:37:08Z 6 application/pdf http://hdl.handle.net/10138/347045 eng eng LREC 2022, THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION 979-10-95546-72-6 Ivanova , S , Washington , J & Tyers , F M 2022 , A Free/Open-Source Morphological Analyser and Generator for Sakha . in LREC 2022, THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION : LREC 2022 Conference Proceedings . European Languages Resources Association (ELRA) , pp. 5137-5142 , Language Resources and Evaluation Conference , Marseille , France , 21/06/2022 . < http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.550.pdf > conference f2726d68-5afc-4f70-b01b-acfab15d28a3 http://hdl.handle.net/10138/347045 cc_by_nc openAccess info:eu-repo/semantics/openAccess 113 Computer and information sciences Conference contribution publishedVersion 2022 ftunivhelsihelda 2023-12-14T00:13:28Z We present, to our knowledge, the first ever published morphological analyser and generator for Sakha, a marginalised language of Siberia. The transducer, developed using HFST, has coverage of solidly above 90%, and high precision. In the development of the analyser, we have expanded linguistic knowledge about Sakha, and developed strategies for complex grammatical patterns. The transducer is already being used in downstream tasks, including computer assisted language learning applications for linguistic maintenance and computational linguistic shared tasks. Peer reviewed Conference Object Sakha Sakha Siberia HELDA – University of Helsinki Open Repository Sakha
institution Open Polar
collection HELDA – University of Helsinki Open Repository
op_collection_id ftunivhelsihelda
language English
topic 113 Computer and information sciences
spellingShingle 113 Computer and information sciences
Ivanova, Sardana
Washington, Jonathan
Tyers, Francis M.
A Free/Open-Source Morphological Analyser and Generator for Sakha
topic_facet 113 Computer and information sciences
description We present, to our knowledge, the first ever published morphological analyser and generator for Sakha, a marginalised language of Siberia. The transducer, developed using HFST, has coverage of solidly above 90%, and high precision. In the development of the analyser, we have expanded linguistic knowledge about Sakha, and developed strategies for complex grammatical patterns. The transducer is already being used in downstream tasks, including computer assisted language learning applications for linguistic maintenance and computational linguistic shared tasks. Peer reviewed
author2 Department of Computer Science
format Conference Object
author Ivanova, Sardana
Washington, Jonathan
Tyers, Francis M.
author_facet Ivanova, Sardana
Washington, Jonathan
Tyers, Francis M.
author_sort Ivanova, Sardana
title A Free/Open-Source Morphological Analyser and Generator for Sakha
title_short A Free/Open-Source Morphological Analyser and Generator for Sakha
title_full A Free/Open-Source Morphological Analyser and Generator for Sakha
title_fullStr A Free/Open-Source Morphological Analyser and Generator for Sakha
title_full_unstemmed A Free/Open-Source Morphological Analyser and Generator for Sakha
title_sort free/open-source morphological analyser and generator for sakha
publishDate 2022
url http://hdl.handle.net/10138/347045
geographic Sakha
geographic_facet Sakha
genre Sakha
Sakha
Siberia
genre_facet Sakha
Sakha
Siberia
op_relation LREC 2022, THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION
979-10-95546-72-6
Ivanova , S , Washington , J & Tyers , F M 2022 , A Free/Open-Source Morphological Analyser and Generator for Sakha . in LREC 2022, THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION : LREC 2022 Conference Proceedings . European Languages Resources Association (ELRA) , pp. 5137-5142 , Language Resources and Evaluation Conference , Marseille , France , 21/06/2022 . < http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.550.pdf >
conference
f2726d68-5afc-4f70-b01b-acfab15d28a3
http://hdl.handle.net/10138/347045
op_rights cc_by_nc
openAccess
info:eu-repo/semantics/openAccess
_version_ 1787428067515301888

Similar Items