The Arabic ontology – an Arabic wordnet with ontologically clean content

Jarrar, Mustafa

doi:10.3233/ao-200241

Cited by 29 publications

(28 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…similar to the Princeton WordNet for English (Miller et al, 1990). The largest available lexical-semantic resource for Arabic is the Birzeit University's lexicographic database 2 , which contains the Arabic Ontology (Jarrar, 2021(Jarrar, , 2011 and about 400K glosses extracted from about 150 lexicons Alhafi et al, 2019). The problem is that each of the 150 lexicons covers a partial set of glosses and lemmas.…”

Section: Context-gloss Pairs Extractionmentioning

confidence: 99%

See 1 more Smart Citation

ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSD

Al-Hajj¹,

Jarrar²

2021

Proceedings of the Conference Recent Advances in Natural Language Processing - Deep Learning for Natural Language Processing M

Self Cite

View full text Add to dashboard Cite

Section: Context-gloss Pairs Extractionmentioning

confidence: 99%

“…To overcome this challenge, we collected a relatively large set of definitions from the Arabic Ontology (Jarrar, 2021) and multiple Arabic dictionaries available at Birzeit University's lexicographic database then we extracted glosses and contexts from lexicon definitions.…”

Section: Introductionmentioning

confidence: 99%

ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSD

Al-Hajj¹,

Jarrar²

2021

Proceedings of the Conference Recent Advances in Natural Language Processing - Deep Learning for Natural Language Processing M

Self Cite

View full text Add to dashboard Cite

“…Then a vector for each lemma ( i.e., Lemma2Vec) is calculated as following: first all word forms belonging to this lemma are fetched, then their Word2Vec vectors are combined through a mean pooling operation. The lemmatization process was performed using in-house tools and lexicographic databases 1 belonging to Birzeit University (Jarrar, 2021;. In case of a word cannot be lemmatized due to misspelling, incorrect tokenization or in case of foreign word (not included in our database), then the corresponding Lemma2Vec is considered to be its Word2Vec vector.…”

Section: Constructing the Lemma2vec Modelsmentioning

confidence: 99%

“…Additionally, there are some specificities of the Arabic language that might not be known in other languages. Although polysemy and disambiguating are challenging issues in all languages, they might be more challenging in the case of Arabic (Jarrar et al, 2018;Jarrar, 2021) and this for many reasons. For example, the wordšāhd ( ) could bešāhid ( ) which means a witness, oř sāhada ( ) which means watch.…”

Section: Introductionmentioning

confidence: 99%

LU-BZU at SemEval-2021 Task 2: Word2Vec and Lemma2Vec performance in Arabic Word-in-Context disambiguation

Al-Hajj¹,

Jarrar²

2021

Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

Self Cite

View full text Add to dashboard Cite

This paper presents a set of experiments to evaluate and compare between the performance of using CBOW Word2Vec and Lemma2Vec models for Arabic Word-in-Context (WiC) disambiguation without using sense inventories or sense embeddings. As part of the SemEval-2021 Shared Task 2 on WiC disambiguation, we used the dev.ar-ar dataset (2k sentence pairs) to decide whether two words in a given sentence pair carry the same meaning. We used two Word2Vec models: Wiki-CBOW, a pre-trained model on Arabic Wikipedia, and another model we trained on large Arabic corpora of about 3 billion tokens. Two Lemma2Vec models was also constructed based on the two Word2Vec models. Each of the four models was then used in the WiC disambiguation task, and then evaluated on the SemEval-2021 test.ar-ar dataset. At the end, we reported the performance of different models and compared between using lemma-based and word-based models.

show abstract

“…A set of senses is called synset. Concepts and senses are described by attributes [9]. Ontologies can be represented as graphs.…”

Section: Literature Reviewmentioning

confidence: 99%

Automated Arabic Essay Scoring Based on Hybrid Stemming With Wordnet

Alobed

Altrad

Bakar

et al. 2021

MJCS

View full text Add to dashboard Cite

Schools, universities, and other educational institutions have been forced to close their doors because of the coronavirus outbreak. E-learning has become an option and has long been discussed about the need to integrate it into the educational process-learning uses a variety of evaluation methods, one of which is the essay. This research introduces a new model for Arabic Automated Essay Grading (AAEG) that has been developed to reduce human bias mistakes and costs while saving time. However, (AAEG) is still in its infancy. The model relies on new hybrid stemming with Arabic WordNet (AWN). The primary goal of stemming is reducing inflectional forms of words to root words. The hybrid method is based on different techniques: Extended Light Stemmer, ISRI, and looking at tables (AWN). Data used in this study consists of 3050 words with their roots were retrieved from (AWN) and then stemmed using algorithms (Light10, ISRI, Hybrid...). For evaluation, the metrics used were accuracy, precision, recall, and F1-score. While comparing the performance of the different stemming algorithms, the hybrid stemming method had the greatest results, therefore the (AAEG) will improve with Hybrid Stemming.

show abstract

The Arabic ontology – an Arabic wordnet with ontologically clean content

Cited by 29 publications

References 41 publications

ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSD

ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSD

LU-BZU at SemEval-2021 Task 2: Word2Vec and Lemma2Vec performance in Arabic Word-in-Context disambiguation

Automated Arabic Essay Scoring Based on Hybrid Stemming With Wordnet

Contact Info

Product

Resources

About