Standard

Estimating syntagmatic association strength using distributional word re presentations. / Bukia, G. T.; Protopopova, E. V.; Panicheva, P. V.; Mitrofanova, O. A.

в: Komp'juternaja Lingvistika i Intellektual'nye Tehnologii, 01.01.2016, стр. 112-121.

Результаты исследований: Научные публикации в периодических изданияхстатья в журнале по материалам конференцииРецензирование

Harvard

Bukia, GT, Protopopova, EV, Panicheva, PV & Mitrofanova, OA 2016, 'Estimating syntagmatic association strength using distributional word re presentations', Komp'juternaja Lingvistika i Intellektual'nye Tehnologii, стр. 112-121.

APA

Bukia, G. T., Protopopova, E. V., Panicheva, P. V., & Mitrofanova, O. A. (2016). Estimating syntagmatic association strength using distributional word re presentations. Komp'juternaja Lingvistika i Intellektual'nye Tehnologii, 112-121.

Vancouver

Bukia GT, Protopopova EV, Panicheva PV, Mitrofanova OA. Estimating syntagmatic association strength using distributional word re presentations. Komp'juternaja Lingvistika i Intellektual'nye Tehnologii. 2016 Янв. 1;112-121.

Author

Bukia, G. T. ; Protopopova, E. V. ; Panicheva, P. V. ; Mitrofanova, O. A. / Estimating syntagmatic association strength using distributional word re presentations. в: Komp'juternaja Lingvistika i Intellektual'nye Tehnologii. 2016 ; стр. 112-121.

BibTeX

@article{9869fc013d6c4bb9b6c03c8fe8c4d3e5,
title = "Estimating syntagmatic association strength using distributional word re presentations",
abstract = "In the paper we present distributed vector space models based on word embeddings and a specific association-oriented count-based distributional algorithm which have been applied to measuring association strength in Russian syntagmatic relations (namely, between nouns and adjectives). We discuss the compositional properties of the vectors representing nouns, adjectives and adjective-noun compositions and propose two methods of detecting the syntactic association possibility. The accuracy of the proposed measures is evaluated by means of a pseudo-disambiguation test procedure and all models show considerably high results. The errors are manually annotated, and the model errors are classified in terms of their linguistic nature and compositionality features.",
keywords = "Adjective-noun phrases, Association measures, Compositional collocations, Distributional semantics, Pseudo-disambiguation, Russian corpora, Word2Vec",
author = "Bukia, {G. T.} and Protopopova, {E. V.} and Panicheva, {P. V.} and Mitrofanova, {O. A.}",
year = "2016",
month = jan,
day = "1",
language = "English",
pages = "112--121",
journal = "Компьютерная лингвистика и интеллектуальные технологии",
issn = "2221-7932",
publisher = "Российский государственный гуманитарный университет",
note = "2016 International Conference on Computational Linguistics and Intellectual Technologies, Dialogue 2016 ; Conference date: 01-06-2016 Through 04-06-2016",

}

RIS

TY - JOUR

T1 - Estimating syntagmatic association strength using distributional word re presentations

AU - Bukia, G. T.

AU - Protopopova, E. V.

AU - Panicheva, P. V.

AU - Mitrofanova, O. A.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - In the paper we present distributed vector space models based on word embeddings and a specific association-oriented count-based distributional algorithm which have been applied to measuring association strength in Russian syntagmatic relations (namely, between nouns and adjectives). We discuss the compositional properties of the vectors representing nouns, adjectives and adjective-noun compositions and propose two methods of detecting the syntactic association possibility. The accuracy of the proposed measures is evaluated by means of a pseudo-disambiguation test procedure and all models show considerably high results. The errors are manually annotated, and the model errors are classified in terms of their linguistic nature and compositionality features.

AB - In the paper we present distributed vector space models based on word embeddings and a specific association-oriented count-based distributional algorithm which have been applied to measuring association strength in Russian syntagmatic relations (namely, between nouns and adjectives). We discuss the compositional properties of the vectors representing nouns, adjectives and adjective-noun compositions and propose two methods of detecting the syntactic association possibility. The accuracy of the proposed measures is evaluated by means of a pseudo-disambiguation test procedure and all models show considerably high results. The errors are manually annotated, and the model errors are classified in terms of their linguistic nature and compositionality features.

KW - Adjective-noun phrases

KW - Association measures

KW - Compositional collocations

KW - Distributional semantics

KW - Pseudo-disambiguation

KW - Russian corpora

KW - Word2Vec

UR - http://www.scopus.com/inward/record.url?scp=85020439309&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85020439309

SP - 112

EP - 121

JO - Компьютерная лингвистика и интеллектуальные технологии

JF - Компьютерная лингвистика и интеллектуальные технологии

SN - 2221-7932

T2 - 2016 International Conference on Computational Linguistics and Intellectual Technologies, Dialogue 2016

Y2 - 1 June 2016 through 4 June 2016

ER -

ID: 47480962