Open AccessExtending phpMorhy with dialect words
Author(s) -
Maxim Gromov,
Svetlana S. Zemicheva
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1680/1/012014
Subject(s) - computer science , word (group theory) , natural language processing , index (typography) , process (computing) , artificial intelligence , stop words , machine readable dictionary , inverse , linguistics , information retrieval , world wide web , programming language , philosophy
This paper describes the work done to create a tool for adding new (dialect) words into the dictionary of phpMorphy. PhpMorphy is a tool written in PHP which helps to annotate a word with grammatical information. It was chosen because it needs not to be trained and it can be integrated into PHP based text corpora search system relatively simply. The search is planned to be done over inverse index of words. The search requests are supposed to contain desired grammatical description of words (eg, “find all feminine adjectives”, etc.). For that reason inverse index should contain grammatical information. The process of adding new words into phpMorphy dictionary technically is not hard however it is time consuming and tedious. To facilitate this work the mentioned tool was developed. Also paper describes the process how the words to add into the phpMorphy dictionary were selected. The words from the given dialect dictionary were run through phpMorphy. If phpMorphy correctly recognizes a word, then it should not be added into the phpMorphy dictionary. Otherwise it should be.