Real-valued syntactic word vectors
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Real-valued syntactic word vectors. / Basirat, A.; Nivre, J.
In: Journal of Experimental and Theoretical Artificial Intelligence, Vol. 32, No. 4, 03.07.2020, p. 557-579.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Real-valued syntactic word vectors
AU - Basirat, A.
AU - Nivre, J.
N1 - Publisher Copyright: © 2019, © 2019 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
PY - 2020/7/3
Y1 - 2020/7/3
N2 - We introduce a word embedding method that generates a set of real-valued word vectors from a distributional semantic space. The semantic space is built with a set of context units (words) which are selected by an entropy-based feature selection approach with respect to the certainty involved in their contextual environments. We show that the most predictive context of a target word is its preceding word. An adaptive transformation function is also introduced that reshapes the data distribution to make it suitable for dimensionality reduction techniques. The final low-dimensional word vectors are formed by the singular vectors of a matrix of transformed data. We show that the resulting word vectors are as good as other sets of word vectors generated with popular word embedding methods.
AB - We introduce a word embedding method that generates a set of real-valued word vectors from a distributional semantic space. The semantic space is built with a set of context units (words) which are selected by an entropy-based feature selection approach with respect to the certainty involved in their contextual environments. We show that the most predictive context of a target word is its preceding word. An adaptive transformation function is also introduced that reshapes the data distribution to make it suitable for dimensionality reduction techniques. The final low-dimensional word vectors are formed by the singular vectors of a matrix of transformed data. We show that the resulting word vectors are as good as other sets of word vectors generated with popular word embedding methods.
KW - context selection
KW - dependency parsing
KW - entropy
KW - singular value decomposition
KW - transformation
KW - Word embeddings
UR - http://www.scopus.com/inward/record.url?scp=85071012514&partnerID=8YFLogxK
U2 - 10.1080/0952813X.2019.1653385
DO - 10.1080/0952813X.2019.1653385
M3 - Journal article
AN - SCOPUS:85071012514
VL - 32
SP - 557
EP - 579
JO - Journal of Experimental and Theoretical Artificial Intelligence
JF - Journal of Experimental and Theoretical Artificial Intelligence
SN - 0952-813X
IS - 4
ER -
ID: 366046134