Coreference Resolution

Student: Zhadaev Nikita

Educational Programme: Fundamental and Computational Linguistics (Bachelor)

Final Grade: 9

Year of Graduation: 2016

This work reports on the expansion of well-studied algorithms on anaphora resolution with syntactic features in texts written in Russian language. The state-of-the-art methods to resolve anaphoric relations in Russian in general do not take into account the dependencies provided by syntactic rules, except the basics. NLP scientists already investigated the importance of syntactic features in anaphora resolution in different languages, e.g. English. Therefore, our aim was to describe the possibilities provided by syntactic features in Russian to improve coherent information recognition’s system. Firstly, I implemented the algorithms using same features that were described in recent works for Russian language. Secondly, I investigated the influence, that Russian syntax can provide to the anaphora resolution system. During the three experiments, I managed to increase the accuracy and the precision of the anaphora resolution system by 12 percent.

Full text (added June 4, 2016)

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