Development of a Software Component to Identify the Chronological Order of the Terms by the Method of Word Formation

Abstract

The relationship of words is an interesting problem of linguistics of the Russian language, which is not so easy to solve. The relationship between related words is not always clear due to changes in language. And close and similar in origin words become quite unlike each other. Automatically understand how two words are connected-a non-trivial task. To implement the task of finding the chronological order of occurrence of terms requires methods allowing two given words to determine the sequence of their appearance relative to each other. The proposed work aims at developing universal methods for identifying the chronological order in which words occur. There are three main methods-the method of word formation, the method of etymological dictionaries, the method of hyponyms and hyperonyms. The main attention is paid to the method of word formation, as one of the main for solving the problem. The basis of the method is a comparison of the morphemic structure of given words. According to the method of word formation, the corresponding method can be divided into several ways in relation to the task: the prefix method, the suffix method, the prefix-suffix method, the suffixless method and the fusion method. The software component is implemented in such a way that for two words on the input you can find out how one word is formed from another. In determining the specific method of word formation, the difference in the morphemic composition of the studied words is used. The system shows the best results for the suffixless method. To analyze the accuracy of the system, a sample was prepared and the accuracy of the system was evaluated. Thus, three methods are proposed to solve the problem of ranking words by the time of their appearance and identifying the chronological order of their occurrence. One of the methods - the method of word formation-is implemented in practice and shows a good result on the collected test sample.

Keywords

• method of word formation
• morphemic analysis
• program component
• chronological order
• terminology