@inproceedings{czerniak-ui-dhonnchadha-2024-towards,
title = "Towards Semantic Tagging for {I}rish",
author = "Czerniak, Tim and
U{\'i} Dhonnchadha, Elaine",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1446/",
pages = "16643--16652",
abstract = "Well annotated corpora have been shown to have great value, both in linguistic and non-linguistic research, and in supporting machine-learning and many other non-research activities including language teaching. For minority languages, annotated corpora can help in understanding language usage norms among native and non-native speakers, providing valuable information both for lexicography and for teaching, and helping to combat the decline of speaker numbers. At the same time, minority languages suffer from having fewer available language resources than majority languages, and far less-developed annotation tooling. To date there is very little work in semantic annotation for Irish. In this paper we report on progress to date in the building of a standard tool-set for semantic annotation of Irish, including a novel method for evaluation of semantic annotation. A small corpus of Irish language data has been manually annotated with semantic tags, and manually checked. A semantic type tagging framework has then been developed using existing technologies, and using a semantic lexicon that has been built from a variety of sources. Semantic disambiguation methods have been added with a view to increasing accuracy. That framework has then been tested using the manually tagged corpus, resulting in over 90{\%} lexical coverage and almost 80{\%} tag accuracy. Development is ongoing as part of a larger corpus development project, and plans include expansion of the manually tagged corpus, expansion of the lexicon, and exploration of further disambiguation methods. As the first semantic tagger for Irish, to our knowledge, it is hoped that this research will form a sound basis for semantic annotation of Irish corpora in to the future."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="czerniak-ui-dhonnchadha-2024-towards">
<titleInfo>
<title>Towards Semantic Tagging for Irish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Czerniak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elaine</namePart>
<namePart type="family">Uí Dhonnchadha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</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">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Well annotated corpora have been shown to have great value, both in linguistic and non-linguistic research, and in supporting machine-learning and many other non-research activities including language teaching. For minority languages, annotated corpora can help in understanding language usage norms among native and non-native speakers, providing valuable information both for lexicography and for teaching, and helping to combat the decline of speaker numbers. At the same time, minority languages suffer from having fewer available language resources than majority languages, and far less-developed annotation tooling. To date there is very little work in semantic annotation for Irish. In this paper we report on progress to date in the building of a standard tool-set for semantic annotation of Irish, including a novel method for evaluation of semantic annotation. A small corpus of Irish language data has been manually annotated with semantic tags, and manually checked. A semantic type tagging framework has then been developed using existing technologies, and using a semantic lexicon that has been built from a variety of sources. Semantic disambiguation methods have been added with a view to increasing accuracy. That framework has then been tested using the manually tagged corpus, resulting in over 90% lexical coverage and almost 80% tag accuracy. Development is ongoing as part of a larger corpus development project, and plans include expansion of the manually tagged corpus, expansion of the lexicon, and exploration of further disambiguation methods. As the first semantic tagger for Irish, to our knowledge, it is hoped that this research will form a sound basis for semantic annotation of Irish corpora in to the future.</abstract>
<identifier type="citekey">czerniak-ui-dhonnchadha-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1446/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>16643</start>
<end>16652</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Semantic Tagging for Irish
%A Czerniak, Tim
%A Uí Dhonnchadha, Elaine
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F czerniak-ui-dhonnchadha-2024-towards
%X Well annotated corpora have been shown to have great value, both in linguistic and non-linguistic research, and in supporting machine-learning and many other non-research activities including language teaching. For minority languages, annotated corpora can help in understanding language usage norms among native and non-native speakers, providing valuable information both for lexicography and for teaching, and helping to combat the decline of speaker numbers. At the same time, minority languages suffer from having fewer available language resources than majority languages, and far less-developed annotation tooling. To date there is very little work in semantic annotation for Irish. In this paper we report on progress to date in the building of a standard tool-set for semantic annotation of Irish, including a novel method for evaluation of semantic annotation. A small corpus of Irish language data has been manually annotated with semantic tags, and manually checked. A semantic type tagging framework has then been developed using existing technologies, and using a semantic lexicon that has been built from a variety of sources. Semantic disambiguation methods have been added with a view to increasing accuracy. That framework has then been tested using the manually tagged corpus, resulting in over 90% lexical coverage and almost 80% tag accuracy. Development is ongoing as part of a larger corpus development project, and plans include expansion of the manually tagged corpus, expansion of the lexicon, and exploration of further disambiguation methods. As the first semantic tagger for Irish, to our knowledge, it is hoped that this research will form a sound basis for semantic annotation of Irish corpora in to the future.
%U https://aclanthology.org/2024.lrec-main.1446/
%P 16643-16652
Markdown (Informal)
[Towards Semantic Tagging for Irish](https://aclanthology.org/2024.lrec-main.1446/) (Czerniak & Uí Dhonnchadha, LREC-COLING 2024)
ACL
- Tim Czerniak and Elaine Uí Dhonnchadha. 2024. Towards Semantic Tagging for Irish. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 16643–16652, Torino, Italia. ELRA and ICCL.