Looking for Hyponyms in Vector Space.
Accepted version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Rei, Marek
Briscoe, Ted
Abstract
The task of detecting and generating hyponyms is at the core of semantic understanding of language, and has numerous practical applications. We investigate how neural network embeddings perform on this task, compared to dependency-based vector space models, and evaluate a range of similarity measures on hyponym generation. A new asymmetric similarity measure and a combination approach are described, both of which significantly improve precision. We release three new datasets of lexical vector representations trained on the BNC and our evaluation dataset for hyponym generation.
Description
Keywords
Journal Title
CoNLL
Conference Name
Eighteenth Conference on Computational Natural Language Learning
Journal ISSN
Volume Title
Publisher
ACL