Learning Lexical Subspaces in a Distributional Vector Space

In this paper, we propose LexSub, a novel approach towards unifying lexical and distributional semantics. We inject knowledge about lexical-semantic relations into distributional word embeddings by defining subspaces of the distributional vector space in which a lexical relatio...

Full description

Bibliographic Details
Main Authors: Arora, Kushal, Chakraborty, Aishik, Cheung, Jackie C. K.
Format: Article
Language:English
Published: The MIT Press 2020-07-01
Series:Transactions of the Association for Computational Linguistics
Online Access:https://www.mitpressjournals.org/doi/abs/10.1162/tacl_a_00316