@inproceedings{avetisyan-2022-dialects,
title = "Dialects Identification of {A}rmenian Language",
author = "Avetisyan, Karen",
editor = "Khurshudyan, Victoria and
Tomeh, Nadi and
Nouvel, Damien and
Donabedian, Anaid and
Vidal-Gorene, Chahan",
booktitle = "Proceedings of the Workshop on Processing Language Variation: Digital Armenian (DigitAm) within the 13th Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.digitam-1.2/",
pages = "8--12",
abstract = "The Armenian language has many dialects that differ from each other syntactically, morphologically, and phonetically. In this work, we implement and evaluate models that determine the dialect of a given passage of text. The proposed models are evaluated for the three major variations of the Armenian language: Eastern, Western, and Classical. Previously, there were no instruments of dialect identification in the Armenian language. The paper presents three approaches: a statistical which relies on a stop words dictionary, a modified statistical one with a dictionary of most frequently encountered words, and the third one that is based on Facebook`s fastText language identification neural network model. Two types of neural network models were trained, one with the usage of pre-trained word embeddings and the other without. Approaches were tested on sentence-level and document-level data. The results show that the neural network-based method works sufficiently better than the statistical ones, achieving almost 98{\%} accuracy at the sentence level and nearly 100{\%} at the document level."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="avetisyan-2022-dialects">
<titleInfo>
<title>Dialects Identification of Armenian Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Avetisyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Processing Language Variation: Digital Armenian (DigitAm) within the 13th Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Khurshudyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damien</namePart>
<namePart type="family">Nouvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaid</namePart>
<namePart type="family">Donabedian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chahan</namePart>
<namePart type="family">Vidal-Gorene</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>
</relatedItem>
<abstract>The Armenian language has many dialects that differ from each other syntactically, morphologically, and phonetically. In this work, we implement and evaluate models that determine the dialect of a given passage of text. The proposed models are evaluated for the three major variations of the Armenian language: Eastern, Western, and Classical. Previously, there were no instruments of dialect identification in the Armenian language. The paper presents three approaches: a statistical which relies on a stop words dictionary, a modified statistical one with a dictionary of most frequently encountered words, and the third one that is based on Facebook‘s fastText language identification neural network model. Two types of neural network models were trained, one with the usage of pre-trained word embeddings and the other without. Approaches were tested on sentence-level and document-level data. The results show that the neural network-based method works sufficiently better than the statistical ones, achieving almost 98% accuracy at the sentence level and nearly 100% at the document level.</abstract>
<identifier type="citekey">avetisyan-2022-dialects</identifier>
<location>
<url>https://aclanthology.org/2022.digitam-1.2/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>8</start>
<end>12</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dialects Identification of Armenian Language
%A Avetisyan, Karen
%Y Khurshudyan, Victoria
%Y Tomeh, Nadi
%Y Nouvel, Damien
%Y Donabedian, Anaid
%Y Vidal-Gorene, Chahan
%S Proceedings of the Workshop on Processing Language Variation: Digital Armenian (DigitAm) within the 13th Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F avetisyan-2022-dialects
%X The Armenian language has many dialects that differ from each other syntactically, morphologically, and phonetically. In this work, we implement and evaluate models that determine the dialect of a given passage of text. The proposed models are evaluated for the three major variations of the Armenian language: Eastern, Western, and Classical. Previously, there were no instruments of dialect identification in the Armenian language. The paper presents three approaches: a statistical which relies on a stop words dictionary, a modified statistical one with a dictionary of most frequently encountered words, and the third one that is based on Facebook‘s fastText language identification neural network model. Two types of neural network models were trained, one with the usage of pre-trained word embeddings and the other without. Approaches were tested on sentence-level and document-level data. The results show that the neural network-based method works sufficiently better than the statistical ones, achieving almost 98% accuracy at the sentence level and nearly 100% at the document level.
%U https://aclanthology.org/2022.digitam-1.2/
%P 8-12
Markdown (Informal)
[Dialects Identification of Armenian Language](https://aclanthology.org/2022.digitam-1.2/) (Avetisyan, DigitAm 2022)
ACL
- Karen Avetisyan. 2022. Dialects Identification of Armenian Language. In Proceedings of the Workshop on Processing Language Variation: Digital Armenian (DigitAm) within the 13th Language Resources and Evaluation Conference, pages 8–12, Marseille, France. European Language Resources Association.