A Thematic Coherence Study of a Bilingual Corpus of Articles on Oil and Gas Research
- Authors: Krasnov F.V.1, Shvartsman M.E.2,3, Dimentov A.V.2, Sen A.I.4
-
Affiliations:
- Gazpromneft Research and Development Center
- National Electronic Information Consortium
- Russian State Library
- St. Petersburg State University
- Issue: Vol 53, No 3 (2019)
- Pages: 138-142
- Section: Automation of Text Processing
- URL: https://journal-vniispk.ru/0005-1055/article/view/150310
- DOI: https://doi.org/10.3103/S0005105519030075
- ID: 150310
Cite item
Abstract
Structural differences between scientific articles that arise from their translation from Russian into English are studied using the modal topic modeling technique. Each collected document is represented by two modes, that is, English and Russian. As a result of the topic modeling, the Φ and Θ bimodal matrices are obtained. Analysis of the Φ matrix showed that the topics were divided according to the degree of conformity between Russian and English terms when the words are considered in descending order of probability. For 90% of the topics, the English words fully match the Russian ones. Analysis of the Θ matrix showed that for 99% of the documents there is a subject with a value greater than 0.95. Thus, most of the documents are monotopical, which does not depend on the document language.
Keywords
About the authors
F. V. Krasnov
Gazpromneft Research and Development Center
Author for correspondence.
Email: Krasnov.FV@gazpromneft-ntc.ru
Russian Federation, St. Petersburg, 190000
M. E. Shvartsman
National Electronic Information Consortium; Russian State Library
Author for correspondence.
Email: shvar@neicon.ru
Russian Federation, Moscow, 115114; Moscow, 119019
A. V. Dimentov
National Electronic Information Consortium
Author for correspondence.
Email: adimentov@neicon.ru
Russian Federation, Moscow, 115114
A. I. Sen
St. Petersburg State University
Author for correspondence.
Email: anastasiia.sen@apmath.spbgu.ru
Russian Federation, St. Petersburg, 199034
Supplementary files
