De-Conflated Semantic Representations

TL;DR

This paper introduces a de-conflation technique for semantic word representations that leverages semantic networks to produce accurate, multi-sense embeddings with high coverage, outperforming previous methods on multiple datasets.

Contribution

It presents a novel approach that effectively generates reliable sense-specific representations, including for infrequent senses, by utilizing deep semantic network knowledge.

Findings

Achieved state-of-the-art results on six datasets across two semantic similarity tasks.

Demonstrated high coverage and accuracy for infrequent word senses.

Outperformed previous sense representation methods.

Abstract

One major deficiency of most semantic representation techniques is that they usually model a word type as a single point in the semantic space, hence conflating all the meanings that the word can have. Addressing this issue by learning distinct representations for individual meanings of words has been the subject of several research studies in the past few years. However, the generated sense representations are either not linked to any sense inventory or are unreliable for infrequent word senses. We propose a technique that tackles these problems by de-conflating the representations of words based on the deep knowledge it derives from a semantic network. Our approach provides multiple advantages in comparison to the past work, including its high coverage and the ability to generate accurate representations even for infrequent word senses. We carry out evaluations on six datasets across two semantic similarity tasks and report state-of-the-art results on most of them.