• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Student
Title
Supervisor
Faculty
Educational Programme
Final Grade
Year of Graduation
Vasiliy Vdovkin
Methods of Text Summarization and Extracting Key Information From Russian News Articles
7
2018
This work describes implementation of the service that can significantly improve user experience in news content consumption by using Natural Language Processing (NLP for short). This service analyses stream of news articles from russian media web-sites in real-time, groups news by events and extracts the most valuable information about the events.

To implement this service we first research and then use models and methods from NLP to find suitable solution for the following problems: normalization, vectorization, clusterization and summarization of text.

Clusterization allows us to automatically group news by events. In order for this to work, we collect the data from web-sites of media and train TF-IDF model allows to use K-means algorithm for news clusterization. Summarization depends on SimBasic and DivRank models and extracts the most informative sentences from the event-cluster. We compare and evaluate the proposed solutions.

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