SeifedinS/Amharic-Text-Normalization

### Date created I have created this project in 27 March 2021. ### Project Title Amharic Text Normalization ### Description All areas of language and speech technology, directly or indirectly, require handling of real text. In addition to ordinary words and names, the real text contains non-standard words (NSW), including numbers, abbreviations, dates, currency, amounts, and acronyms. Typically, one cannot find NSWs in a dictionary, nor can one find their pronunciation by an application of ordinary “letter-to-sound” rules. It is desirable to “normalize” text by replacing such non-standard words with a consistently formatted and contextually appropriate variant in several applications including machine translation, topic detection, text summarization, text-to-speech (TTS) systems, training of automatic speech recognizers. ### Purpose of the project Text normalization or the conversion of NSW into standard words is an important problem. It is also quite a complex problem, due to the range of different kinds of Non-standard, the special processing required for each case, and the propensity for ambiguity among NSW's as a class. Unfortunately, text normalization is not a problem that has received a great deal of attention. Currently, many normalization systems are available mainly for ‘major’ languages such as English, Russia etc. and successful results are obtained in various application areas. However, thousands of the world’s languages lack such technologies, and researches in the area are quit very view. The general objective of the research is to design efficient machine learning approach for Amharic language text normalization that converts standard and non-standard words encountered in real-world text reading. ### Files used - Amharic text ### Software requirements - You should have Python 3 - A text editor, like Sublime or Atom. - A terminal application (Terminal on Mac and Linux or Cygwin on Windows).