Please use this identifier to cite or link to this item:
Title: Automatic Extraction of Synonymous Collocation Pairs from a Text Corpus
Authors: Khairova, N. F.
Petrasova, S. V.
Lewoniewski, Włodzimierz
Mamyrbayev, Orken
Mukhsina, Kuralay
Issue Date: 2018
Publisher: Polskie Towarzystwo Informatyczne, Poland
Citation: Automatic Extraction of Synonymous Collocation Pairs from a Text Corpus / N. Khairova [et al.] // Proceedings of the 2018 Federated Conference on Computer Science and Information Systems September (FedCSIS 2018), September 9-12, 2018, Poznań, Poland. Vol.15: Annals of Computer Science and Information Systems / ed. M. Ganzha, L. Maciaszek, M. Paprzycki. – Warsaw : PTI, 2018. – P. 485-488.
Abstract: Automatic extraction of synonymous collocation pairs from text corpora is a challenging task of NLP. In order to search collocations of similar meaning in English texts, we use logical-algebraic equations. These equations combine grammatical and semantic characteristics of words of substantive, attributive and verbal collocations types. With Stanford POS tagger and Stanford Universal Dependencies parser, we identify the grammatical characteristics of words. We exploit WordNet synsets to pick synonymous words of collocations. The potential synonymous word combinations found are checked for compliance with grammatical and semantic characteristics of the proposed logical-linguistic equations. Our dataset includes more than half a million Wikipedia articles from a few portals. The experiment shows that the more frequent synonymous collocations occur in texts, the more related topics of the texts might be. The precision of synonymous collocations search in our experiment has achieved the results close to other studies like ours.
Appears in Collections:Кафедра "Інтелектуальні комп'ютерні системи"

Files in This Item:
File Description SizeFormat 
Khairova_Automatic_extraction_2018.pdf145,66 kBAdobe PDFThumbnail
Show full item record  Google Scholar

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.