|
Title:
|
FINDING SYNONYMS IN A SYNTACTICALLY
CONSTRAINED VECTOR SPACE MODEL |
|
Author(s):
|
Dongqiang Yang, Xiaodong Sun and Pikun Wang |
|
ISBN:
|
978-989-8704-34-4 |
|
Editors:
|
Pedro Isaías and Hans Weghorn |
|
Year:
|
2021 |
|
Edition:
|
Single |
|
Type:
|
Full |
|
First Page:
|
26 |
|
Last Page:
|
33 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Distributional semantics in a vector space model plays an important role in natural language engineering. Apart from the
word co-occurrences in plain context, the role of syntactic dependencies in deriving distributional semantics has not yet
been fully investigated. We systematically investigate the salience of syntactic dependencies in accounting for
distributional similarity. We first categorize the syntactic dependencies of words into four raw co-occurrence matrices
that are respectively transformed into the second-order compressed matrices, then we systematically evaluate them in the
TOEFL synonym test. Our results show that the semantic features of nouns mostly consist of their modifiers and their
head nouns, whereas the semantic features of verbs are mostly explained by verb-modifiers and verb-objects. The
syntactically conditioned contexts can interpret lexical semantics better than the unconditioned one. |
|
|
|
|
|
|
