@inproceedings{kote-etal-2024-universal,
title = "{U}niversal {D}ependencies Treebank for Standard {A}lbanian: A New Approach",
author = {Kote, Nelda and
Rushiti, Rozana and
{\c{C}}epani, Anila and
Haveriku, Alba and
Trandafili, Evis and
Me{\c{c}}e, Elinda Kajo and
Rakipllari, Elsa Sk{\"e}nderi and
Xhanari, Lindita and
Deda, Albana},
booktitle = "Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024)",
month = sep,
year = "2024",
address = "Sofia, Bulgaria",
publisher = "Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences",
url = "https://aclanthology.org/2024.clib-1.7",
pages = "80--89",
abstract = "In this paper, we present a Universal Dependencies (UD) treebank for the Standard Albanian Language (SAL), annotated by expert linguistics supported by information technology professionals. The annotated treebank consists of 24,537 tokens (1,400 sentences) and includes annotation for syntactic dependencies, part-of-speech tags, morphological features, and lemmas. This treebank represents the largest UD treebank available for SAL. In order to overcome annotation challenges in SAL within the UD framework, we delicately balanced the preservation of the richness of SAL grammar while adapting the UD tagset and addressing unique language-specific features for a unified annotation. We discuss the criteria followed to select the sentences included in the treebank and address the most significant linguistic considerations when adapting the UD framework conform to the grammar of the SAL. Our efforts contribute to the advancement of linguistic analyses and Natural Language Processing (NLP) in the SAL. The treebank will be made available online under an open license so that to provide the possibility for further developments of NLP tools based on the Artificial Intelligence (AI) models for the Albanian language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kote-etal-2024-universal">
<titleInfo>
<title>Universal Dependencies Treebank for Standard Albanian: A New Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nelda</namePart>
<namePart type="family">Kote</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rozana</namePart>
<namePart type="family">Rushiti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anila</namePart>
<namePart type="family">Çepani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alba</namePart>
<namePart type="family">Haveriku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evis</namePart>
<namePart type="family">Trandafili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elinda</namePart>
<namePart type="given">Kajo</namePart>
<namePart type="family">Meçe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elsa</namePart>
<namePart type="given">Skënderi</namePart>
<namePart type="family">Rakipllari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lindita</namePart>
<namePart type="family">Xhanari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albana</namePart>
<namePart type="family">Deda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024)</title>
</titleInfo>
<originInfo>
<publisher>Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences</publisher>
<place>
<placeTerm type="text">Sofia, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present a Universal Dependencies (UD) treebank for the Standard Albanian Language (SAL), annotated by expert linguistics supported by information technology professionals. The annotated treebank consists of 24,537 tokens (1,400 sentences) and includes annotation for syntactic dependencies, part-of-speech tags, morphological features, and lemmas. This treebank represents the largest UD treebank available for SAL. In order to overcome annotation challenges in SAL within the UD framework, we delicately balanced the preservation of the richness of SAL grammar while adapting the UD tagset and addressing unique language-specific features for a unified annotation. We discuss the criteria followed to select the sentences included in the treebank and address the most significant linguistic considerations when adapting the UD framework conform to the grammar of the SAL. Our efforts contribute to the advancement of linguistic analyses and Natural Language Processing (NLP) in the SAL. The treebank will be made available online under an open license so that to provide the possibility for further developments of NLP tools based on the Artificial Intelligence (AI) models for the Albanian language.</abstract>
<identifier type="citekey">kote-etal-2024-universal</identifier>
<location>
<url>https://aclanthology.org/2024.clib-1.7</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>80</start>
<end>89</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Universal Dependencies Treebank for Standard Albanian: A New Approach
%A Kote, Nelda
%A Rushiti, Rozana
%A Çepani, Anila
%A Haveriku, Alba
%A Trandafili, Evis
%A Meçe, Elinda Kajo
%A Rakipllari, Elsa Skënderi
%A Xhanari, Lindita
%A Deda, Albana
%S Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024)
%D 2024
%8 September
%I Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences
%C Sofia, Bulgaria
%F kote-etal-2024-universal
%X In this paper, we present a Universal Dependencies (UD) treebank for the Standard Albanian Language (SAL), annotated by expert linguistics supported by information technology professionals. The annotated treebank consists of 24,537 tokens (1,400 sentences) and includes annotation for syntactic dependencies, part-of-speech tags, morphological features, and lemmas. This treebank represents the largest UD treebank available for SAL. In order to overcome annotation challenges in SAL within the UD framework, we delicately balanced the preservation of the richness of SAL grammar while adapting the UD tagset and addressing unique language-specific features for a unified annotation. We discuss the criteria followed to select the sentences included in the treebank and address the most significant linguistic considerations when adapting the UD framework conform to the grammar of the SAL. Our efforts contribute to the advancement of linguistic analyses and Natural Language Processing (NLP) in the SAL. The treebank will be made available online under an open license so that to provide the possibility for further developments of NLP tools based on the Artificial Intelligence (AI) models for the Albanian language.
%U https://aclanthology.org/2024.clib-1.7
%P 80-89
Markdown (Informal)
[Universal Dependencies Treebank for Standard Albanian: A New Approach](https://aclanthology.org/2024.clib-1.7) (Kote et al., CLIB 2024)
ACL
- Nelda Kote, Rozana Rushiti, Anila Çepani, Alba Haveriku, Evis Trandafili, Elinda Kajo Meçe, Elsa Skënderi Rakipllari, Lindita Xhanari, and Albana Deda. 2024. Universal Dependencies Treebank for Standard Albanian: A New Approach. In Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024), pages 80–89, Sofia, Bulgaria. Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences.