Semantic analysis of Russian prepositional constructions

Victor Zakharov, Kirill Boyarsky, Anastasia Golovina, Anastasia Kozlova

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The paper deals with semantics of Russian prepositions. We consider prepositional meaning to be the relation found in prepositional constructions where it should be regarded as a special type of relationship between content words. There is a rather small set of common prepositional meanings that we call syntaxemes after G.A. Zolotova that encompass the larger part of the Russian prepositional semantics as a whole. In this paper we propose a methodology of prepositional phrase extraction and syntaxeme identification based on text corpora and corpus statistics. Prepositional construction meaning is detected automatically using the SemSin parser. We demonstrate our methodology on constructions with the polysemous Russian preposition {greek characters) (through).

Original languageEnglish
Title of host publicationRASLAN 2020 - 14th Workshop on Recent Advances in Slavonic Natural Language Processing, Proceedings
EditorsAles Horak, Pavel Rychly, Adam Rambousek
PublisherTribun EU
Pages103-111
Number of pages9
ISBN (Electronic)9788026316008
StatePublished - 2020
Event14th Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2020 - Virtual, Brno, Czech Republic
Duration: 8 Dec 202010 Dec 2020

Publication series

NameRecent Advances in Slavonic Natural Language Processing
Volume2020-December
ISSN (Print)2336-4289

Conference

Conference14th Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2020
Country/TerritoryCzech Republic
CityVirtual, Brno
Period8/12/2010/12/20

Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Information Systems
  • Software

Fingerprint

Dive into the research topics of 'Semantic analysis of Russian prepositional constructions'. Together they form a unique fingerprint.

Cite this