Real-valued Syntactic Word Vectors (RSV) for Greedy Neural Dependency Parsing

Research output: Contribution to journal › Conference article › Research › peer-review

Standard

Real-valued Syntactic Word Vectors (RSV) for Greedy Neural Dependency Parsing. / Basirat, Ali; Nivre, Joakim.

In: NoDaLiDa 2017 - 21st Nordic Conference of Computational Linguistics, Proceedings of the Conference, 2017, p. 20-28.

Research output: Contribution to journal › Conference article › Research › peer-review

Harvard

Basirat, A & Nivre, J 2017, 'Real-valued Syntactic Word Vectors (RSV) for Greedy Neural Dependency Parsing', NoDaLiDa 2017 - 21st Nordic Conference of Computational Linguistics, Proceedings of the Conference, pp. 20-28.

APA

Basirat, A., & Nivre, J. (2017). Real-valued Syntactic Word Vectors (RSV) for Greedy Neural Dependency Parsing. NoDaLiDa 2017 - 21st Nordic Conference of Computational Linguistics, Proceedings of the Conference, 20-28.

Vancouver

Basirat A, Nivre J. Real-valued Syntactic Word Vectors (RSV) for Greedy Neural Dependency Parsing. NoDaLiDa 2017 - 21st Nordic Conference of Computational Linguistics, Proceedings of the Conference. 2017;20-28.

Author

Basirat, Ali ; Nivre, Joakim. / Real-valued Syntactic Word Vectors (RSV) for Greedy Neural Dependency Parsing. In: NoDaLiDa 2017 - 21st Nordic Conference of Computational Linguistics, Proceedings of the Conference. 2017 ; pp. 20-28.

Bibtex

@inproceedings{e4052ecb13d24955bc685bd702faf421,
title = "Real-valued Syntactic Word Vectors (RSV) for Greedy Neural Dependency Parsing",
abstract = "We show that a set of real-valued word vectors formed by right singular vectors of a transformed co-occurrence matrix are meaningful for determining different types of dependency relations between words. Our experimental results on the task of dependency parsing confirm the superiority of the word vectors to the other sets of word vectors generated by popular methods of word embedding. We also study the effect of using these vectors on the accuracy of dependency parsing in different languages versus using more complex parsing architectures.",
author = "Ali Basirat and Joakim Nivre",
note = "Publisher Copyright: {\textcopyright} 2017 Link{\"o}ping University Electronic Press.; 21st Nordic Conference of Computational Linguistics, NoDaLiDa 2017 ; Conference date: 23-05-2017 Through 24-05-2017",
year = "2017",
language = "English",
pages = "20--28",
journal = "NoDaLiDa 2017 - 21st Nordic Conference of Computational Linguistics, Proceedings of the Conference",

}

RIS

TY - GEN

T1 - Real-valued Syntactic Word Vectors (RSV) for Greedy Neural Dependency Parsing

AU - Basirat, Ali

AU - Nivre, Joakim

N1 - Publisher Copyright: © 2017 Linköping University Electronic Press.

PY - 2017

Y1 - 2017

N2 - We show that a set of real-valued word vectors formed by right singular vectors of a transformed co-occurrence matrix are meaningful for determining different types of dependency relations between words. Our experimental results on the task of dependency parsing confirm the superiority of the word vectors to the other sets of word vectors generated by popular methods of word embedding. We also study the effect of using these vectors on the accuracy of dependency parsing in different languages versus using more complex parsing architectures.

AB - We show that a set of real-valued word vectors formed by right singular vectors of a transformed co-occurrence matrix are meaningful for determining different types of dependency relations between words. Our experimental results on the task of dependency parsing confirm the superiority of the word vectors to the other sets of word vectors generated by popular methods of word embedding. We also study the effect of using these vectors on the accuracy of dependency parsing in different languages versus using more complex parsing architectures.

UR - http://www.scopus.com/inward/record.url?scp=85046650668&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85046650668

SP - 20

EP - 28

JO - NoDaLiDa 2017 - 21st Nordic Conference of Computational Linguistics, Proceedings of the Conference

JF - NoDaLiDa 2017 - 21st Nordic Conference of Computational Linguistics, Proceedings of the Conference

T2 - 21st Nordic Conference of Computational Linguistics, NoDaLiDa 2017

Y2 - 23 May 2017 through 24 May 2017

ER -

ID: 366047396