Unsupervised Creation of Normalization Dictionaries for Micro-Blogs in Arabic, French and English

Abstract

Text normalisation is a necessity to correctand make more sense of the micro-blogs messages, for information retrieval purposes. Unfortunately, tools and resources of text normalization are rarely shared. In this paper, an approach is presented based onan unsupervised method for text normalization using distributed representations of words, known also as "word embedding", applied on Arabic, French and English Languages. In addition, a tool will be supplied to create dictionaries for micro-blogs normalisation, in a form of pairs of misspelled word with its standard-form word, in the languages: Arabic, French and English. The tool will be available as open source including the resources: word embedding’s models (with vocabulary size of million words for Arabic language model, 5 million words for English language model and 683 thousand words for French language model), and also three normalization dictionaries of 10 thousand pairs in Arabic language, 3 thousand pairs in French language and 18 thousand pairs in English language. The evaluation of the tool shows an average in Normalization success of 96% for English language, 89.5% for Arabic Language and 85% for French Language. Also, the results of using an English language normalization dictionary with a sentiment analysis tool for micro-blog’s messages, show an in crease in f-measure from 58.15 to 59.56.