word representation or word embedding in Persian text
This provides a resource for Persian natural language processing, but it is incremental as it applies existing methods to a new language.
The paper tackled word representation for Persian text by updating GloVe, CBOW, and skip-gram methods to generate embedded vectors, resulting in vectors for 342,362 words across three models.
Text processing is one of the sub-branches of natural language processing. Recently, the use of machine learning and neural networks methods has been given greater consideration. For this reason, the representation of words has become very important. This article is about word representation or converting words into vectors in Persian text. In this research GloVe, CBOW and skip-gram methods are updated to produce embedded vectors for Persian words. In order to train a neural networks, Bijankhan corpus, Hamshahri corpus and UPEC corpus have been compound and used. Finally, we have 342,362 words that obtained vectors in all three models for this words. These vectors have many usage for Persian natural language processing.