AraVec: A set of Arabic Word Embedding Models for use in Arabic NLP
By A. Soliman, Kareem Eissa, Samhaa Rafee Adel El-Beltagy. International Conference on Arabic Computational Linguistics, 2017
518 citations recorded by the source corpus.
Abstract Advancements in neural networks have led to developments in fields like computer vision, speech recognition and natural language processing (NLP). One of the most influential recent developments in NLP is the use of word embeddings, where words are represented as vectors in a continuous space, capturing many syntactic and semantic relations among them. AraVec is a pre-trained distributed word representation (word embedding) open source project which aims to provide the Arabic NLP research community with free to use and powerful word embedding models. The first version of AraVec provides six different word embedding models built on top of three different Arabic content domains; Tweets, World Wide Web pages and Wikipedia Arabic articles. The total number of tokens used to build the models amounts to more than 3,300,000,000. This paper describes the resources used for building the models, the employed data cleaning techniques, the carried out preprocessing step, as well as the details of the employed word embedding creation techniques.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/3924aa213ff891812c66a6909ab902684d3eb107
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Anne Lauscher
- Goran Glavas
- Simone Paolo Ponzetto
- Rafik Takieddin
- Fady Baly
- Hazem M. Hajj
- Wissam Antoun
- Ivan Vulic
Citations in the corpus
- AraBERT: Transformer-based Model for Arabic Language Understanding (2020, methodology): “Arabic word2vec was first attempted by (Soliman et al., 2017), it was then followed by a Fasttext model (Bojanowski et al., 2017) trained on wikipedia data, showing even better performance than what was achieved with word2vec.”
- AraWEAT: Multidimensional Analysis of Biases in Arabic Word Embeddings (2020, methodology): “ vectors. To this end, we compare 100- vs. 300- dimensional embeddings. Furthermore, we analyze the effect of unigram vs. n-gram preprocessing of Arabic text, as offered by pretrained vectors AraVec (Mohammad et al., 2017); (4) corpus size: Lauscher and Glavasˇ (2019) hypothesize that biases might b”