@inproceedings{karev-koychev-2024-generating,
title = "Generating Phonetic Embeddings for {B}ulgarian Words with Neural Networks",
author = "Karev, Lyuboslav and
Koychev, Ivan",
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-1.6",
pages = "71--79",
abstract = "Word embeddings can be considered the cornerstone of modern natural language processing. They are used in many NLP tasks and allow us to create models that can understand the meaning of words. Most word embeddings model the semantics of the words. In this paper, we create phoneme-based word embeddings, which model how a word sounds. This is accomplished by training a neural network that can automatically generate transcriptions of Bulgarian words. We used the Jaccard index and direct comparison metrics to measure the performance of neural networks. The models perform nearly perfectly with the task of generating transcriptions. The model{'}s word embeddings offer versatility across various applications, with its application in automatic paronym detection being particularly notable, as well as the task of detecting the language of origin of a Bulgarian word. The performance of this paronym detection is measured with the standard classifier metrics - accuracy, precision, recall, and F1.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karev-koychev-2024-generating">
<titleInfo>
<title>Generating Phonetic Embeddings for Bulgarian Words with Neural Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lyuboslav</namePart>
<namePart type="family">Karev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Koychev</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>Word embeddings can be considered the cornerstone of modern natural language processing. They are used in many NLP tasks and allow us to create models that can understand the meaning of words. Most word embeddings model the semantics of the words. In this paper, we create phoneme-based word embeddings, which model how a word sounds. This is accomplished by training a neural network that can automatically generate transcriptions of Bulgarian words. We used the Jaccard index and direct comparison metrics to measure the performance of neural networks. The models perform nearly perfectly with the task of generating transcriptions. The model’s word embeddings offer versatility across various applications, with its application in automatic paronym detection being particularly notable, as well as the task of detecting the language of origin of a Bulgarian word. The performance of this paronym detection is measured with the standard classifier metrics - accuracy, precision, recall, and F1.</abstract>
<identifier type="citekey">karev-koychev-2024-generating</identifier>
<location>
<url>https://aclanthology.org/2024.clib-1.6</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>71</start>
<end>79</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Phonetic Embeddings for Bulgarian Words with Neural Networks
%A Karev, Lyuboslav
%A Koychev, Ivan
%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 karev-koychev-2024-generating
%X Word embeddings can be considered the cornerstone of modern natural language processing. They are used in many NLP tasks and allow us to create models that can understand the meaning of words. Most word embeddings model the semantics of the words. In this paper, we create phoneme-based word embeddings, which model how a word sounds. This is accomplished by training a neural network that can automatically generate transcriptions of Bulgarian words. We used the Jaccard index and direct comparison metrics to measure the performance of neural networks. The models perform nearly perfectly with the task of generating transcriptions. The model’s word embeddings offer versatility across various applications, with its application in automatic paronym detection being particularly notable, as well as the task of detecting the language of origin of a Bulgarian word. The performance of this paronym detection is measured with the standard classifier metrics - accuracy, precision, recall, and F1.
%U https://aclanthology.org/2024.clib-1.6
%P 71-79
Markdown (Informal)
[Generating Phonetic Embeddings for Bulgarian Words with Neural Networks](https://aclanthology.org/2024.clib-1.6) (Karev & Koychev, CLIB 2024)
ACL
- Lyuboslav Karev and Ivan Koychev. 2024. Generating Phonetic Embeddings for Bulgarian Words with Neural Networks. In Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024), pages 71–79, Sofia, Bulgaria. Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences.