Scoring Lexical Entailment with a Supervised Directional Similarity Network

ACL 2018

Scoring Lexical Entailment with a Supervised Directional Similarity Network

Jan 29, 2021
|
40 views
|
Details
Absract: We present the Supervised Directional Similarity Network, a novel neural architecture for learning task-specific trans-formation functions on top of general-purpose word embeddings. Relying on only a limited amount of supervision from task-specific scores on a subset of the vocabulary, our architecture is able to generalise and transform a general-purpose distributional vector space to model the relation of lexical entailment. Experiments show excellent perfor-mance on scoring graded lexical entailment, raising the state-of-the-art on the HyperLex dataset by approximately 25%. Authors: Marek Rei, Daniela Gerz, Ivan Vulić (University of Cambridge)

Comments
loading...