Evaluation of Different Approaches to Discourse Analysis in Learner Corpora

Student: Shatova Evelina

Supervisor: Olga Ilyinichna Vinogradova

Educational Programme: Fundamental and Computational Linguistics (Bachelor)

Year of Graduation: 2016

Corpora studies constitute one of the most interesting area in linguistics. Learner corpora is a vital field of research for anyone who is interested in language acquisition and the process of learning. An example of a learner corpus is REALEC (Russian Error-Annotated Learner English Corpus). Among different errors in students’ written works, discourse errors prevail dramatically. Classifying these errors is a very tedious task. Human factors always affect annotators so any automatic annotation program would be of use for them. It is vital to compare different annotating strategies. In this work I analyse REALEC annotating system and ICLE (Université Catholique de Louvain) annotating system. As a result of my research, I have written and give a set of trials to such a program which searches for the specific mistakes and then writes an annotation file. Annotation file with a text then expected to be uploaded to a special folder, so the annotations will be visible on the website.

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