Scoring Lexical Entailment with a Supervised Directional Similarity Network

TL;DR

This paper introduces SDSN, a neural model that learns to transform word embeddings for lexical entailment scoring, significantly improving performance on the HyperLex dataset with minimal supervision.

Contribution

The paper proposes a novel neural architecture that effectively models lexical entailment by learning task-specific transformations with limited supervision.

Findings

Achieved approximately 25% improvement on HyperLex dataset

Demonstrated effective generalization from limited supervision

Outperformed previous state-of-the-art methods

Abstract

We present the Supervised Directional Similarity Network (SDSN), a novel neural architecture for learning task-specific transformation 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 performance on scoring graded lexical entailment, raising the state-of-the-art on the HyperLex dataset by approximately 25%.