Entity and Relation Extraction from Government Documents

Student: Sarkisyan Veronika

Supervisor: Ekaterina Artemova

Educational Programme: Data Science (Master)

Year of Graduation: 2020

The paper provides an overview of existing datasets and models for named entity recognition and relation extraction tasks. Despite the fact that this task can be considered well-studied, most of the general domain datasets do not contain entities common to business tasks. As a result, models trained on academic datasets in the industry show significantly worse quality. As part of the project, the Russian-language corpus RuREBus was annotated. The corpus consists of strategic planning documents of the Ministry of Economic Development of the Russian Federation. The resulting dataset can be used both in academic and in applied problems. The paper considers a model for joint extraction of entities and relations and presents the metrics obtained during its training for the RuREBus corpus.

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