Real-valued syntactic word vectors
Research output: Contribution to journal › Journal article › Research › peer-review
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.
Original language | English |
---|---|
Journal | Journal of Experimental and Theoretical Artificial Intelligence |
Volume | 32 |
Issue number | 4 |
Pages (from-to) | 557-579 |
Number of pages | 23 |
ISSN | 0952-813X |
DOIs | |
Publication status | Published - 3 Jul 2020 |
Externally published | Yes |
Bibliographical note
Publisher Copyright:
© 2019, © 2019 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
- context selection, dependency parsing, entropy, singular value decomposition, transformation, Word embeddings
Research areas
ID: 366046134