@inproceedings{544741374c4643c79ba4e36282f96803,
title = "A Benchmark and Scoring Algorithm for Enriching Arabic Synonyms",
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.",
author = "Sana Ghanem and Mustafa Jarrar and Radi Jarrar and Ibrahim Bounhas",
note = "Publisher Copyright: {\textcopyright} 2023 12th Global Wordnet Conference, GWC 2023. All rights reserved.; 12th Global Wordnet Conference, GWC 2023 ; Conference date: 23-01-2023 Through 27-01-2023",
year = "2023",
month = jan,
day = "27",
language = "English",
series = "12th Global Wordnet Conference, GWC 2023",
publisher = "Association for Computational Linguistics (ACL)",
pages = "274--283",
editor = "German Rigau and Francis Bond and Alexandre Rademaker",
booktitle = "12th Global Wordnet Conference, GWC 2023",
address = "United States",
}