@inproceedings{ghanem-etal-2023-benchmark,
title = "A Benchmark and Scoring Algorithm for Enriching {A}rabic Synonyms",
author = "Ghanem, Sana and
Jarrar, Mustafa and
Jarrar, Radi and
Bounhas, Ibrahim",
editor = "Rigau, German and
Bond, Francis and
Rademaker, Alexandre",
booktitle = "Proceedings of the 12th Global Wordnet Conference",
month = jan,
year = "2023",
address = "University of the Basque Country, Donostia - San Sebastian, Basque Country",
publisher = "Global Wordnet Association",
url = "https://aclanthology.org/2023.gwc-1.34",
pages = "274--283",
abstract = "This paper addresses the task of extending a given synset with additional synonyms taking into account synonymy strength as a fuzzy value. Given a mono/multilingual synset and a threshold (a fuzzy value [0−1]), our goal is to extract new synonyms above this threshold from existing lexicons. We present twofold contributions: an algorithm and a benchmark dataset. The dataset consists of 3K candidate synonyms for 500 synsets. Each candidate synonym is annotated with a fuzzy value by four linguists. The dataset is important for (i) understanding how much linguists (dis/)agree on synonymy, in addition to (ii) using the dataset as a baseline to evaluate our algorithm. Our proposed algorithm extracts synonyms from existing lexicons and computes a fuzzy value for each candidate. Our evaluations show that the algorithm behaves like a linguist and its fuzzy values are close to those proposed by linguists (using RMSE and MAE). The dataset and a demo page are publicly available at https://portal.sina.birzeit.edu/synonyms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghanem-etal-2023-benchmark">
<titleInfo>
<title>A Benchmark and Scoring Algorithm for Enriching Arabic Synonyms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sana</namePart>
<namePart type="family">Ghanem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="family">Jarrar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radi</namePart>
<namePart type="family">Jarrar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Bounhas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Global Wordnet Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Rademaker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Global Wordnet Association</publisher>
<place>
<placeTerm type="text">University of the Basque Country, Donostia - San Sebastian, Basque Country</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper addresses the task of extending a given synset with additional synonyms taking into account synonymy strength as a fuzzy value. Given a mono/multilingual synset and a threshold (a fuzzy value [0−1]), our goal is to extract new synonyms above this threshold from existing lexicons. We present twofold contributions: an algorithm and a benchmark dataset. The dataset consists of 3K candidate synonyms for 500 synsets. Each candidate synonym is annotated with a fuzzy value by four linguists. The dataset is important for (i) understanding how much linguists (dis/)agree on synonymy, in addition to (ii) using the dataset as a baseline to evaluate our algorithm. Our proposed algorithm extracts synonyms from existing lexicons and computes a fuzzy value for each candidate. Our evaluations show that the algorithm behaves like a linguist and its fuzzy values are close to those proposed by linguists (using RMSE and MAE). The dataset and a demo page are publicly available at https://portal.sina.birzeit.edu/synonyms.</abstract>
<identifier type="citekey">ghanem-etal-2023-benchmark</identifier>
<location>
<url>https://aclanthology.org/2023.gwc-1.34</url>
</location>
<part>
<date>2023-01</date>
<extent unit="page">
<start>274</start>
<end>283</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Benchmark and Scoring Algorithm for Enriching Arabic Synonyms
%A Ghanem, Sana
%A Jarrar, Mustafa
%A Jarrar, Radi
%A Bounhas, Ibrahim
%Y Rigau, German
%Y Bond, Francis
%Y Rademaker, Alexandre
%S Proceedings of the 12th Global Wordnet Conference
%D 2023
%8 January
%I Global Wordnet Association
%C University of the Basque Country, Donostia - San Sebastian, Basque Country
%F ghanem-etal-2023-benchmark
%X This paper addresses the task of extending a given synset with additional synonyms taking into account synonymy strength as a fuzzy value. Given a mono/multilingual synset and a threshold (a fuzzy value [0−1]), our goal is to extract new synonyms above this threshold from existing lexicons. We present twofold contributions: an algorithm and a benchmark dataset. The dataset consists of 3K candidate synonyms for 500 synsets. Each candidate synonym is annotated with a fuzzy value by four linguists. The dataset is important for (i) understanding how much linguists (dis/)agree on synonymy, in addition to (ii) using the dataset as a baseline to evaluate our algorithm. Our proposed algorithm extracts synonyms from existing lexicons and computes a fuzzy value for each candidate. Our evaluations show that the algorithm behaves like a linguist and its fuzzy values are close to those proposed by linguists (using RMSE and MAE). The dataset and a demo page are publicly available at https://portal.sina.birzeit.edu/synonyms.
%U https://aclanthology.org/2023.gwc-1.34
%P 274-283
Markdown (Informal)
[A Benchmark and Scoring Algorithm for Enriching Arabic Synonyms](https://aclanthology.org/2023.gwc-1.34) (Ghanem et al., GWC 2023)
ACL