A Comparative Study of Machine Learning Models for Wordforms Morphological Analysis

Student: Lipinskiy Sergey

Educational Programme: Data Science (Master)

Year of Graduation: 2019

This work is dedicated to applying machine learning models in the task of a morpheme analysis of words in Russian. The morpheme analysis implies word’s segmentation into morphs and definition of morphological type of each morph. In this work existing models of morpheme segmentation analysis were reviewed. The series of experiments were made in order to improve the efficiency of the existing model of morpheme segmentation based on the convolutional neuron network. In particular the experiments were implemented in order to modify marking of letters in words of the dataset, as well as to modify the architecture of the neuron network. The multiple versions of the morpheme analysis model were obtained, which were afterwards compared based on the efficiency of their performance.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses