Sharif Digital Repository

Recently, there has been renewed interest in semantic word representation also called word embedding, in a wide variety of natural language processing tasks requiring sophisticated semantic and syntactic information. The quality of word embedding methods is usually evaluated based on English language benchmarks. Nevertheless, only a few studies analyze word embedding for low resource languages such as Persian. In this paper, we perform such an extensive word embedding evaluation in Persian language based on a set of lexical semantics tasks named analogy, concept categorization, and word semantic relatedness. For these evaluation tasks, we provide three benchmark data sets to show the... 

In this paper, recurrent neural networks are applied to language modeling of Persian, using word embedding as word representation. To this aim, unidirectional and bidirectional Long Short-Term Memory (LSTM) networks are used, and the perplexity of Persian language models on a 100-million-word data set is evaluated. The effect of various parameters, including number of hidden layers and size of LSTM units, on the performance of the networks in reducing the perplexity of the models are investigated. Among different LSTM language models, the best perplexity, which is equal to 59.05, is achieved from a 2-layer bidirectional LSTM model. Comparing this value with the perplexity of the classical...