Refining the Distributional Inclusion Hypothesis for Unsupervised Hypernym Identification

Abstract

Several unsupervised methods for hypernym detection have been investigated in distributional semantics. Here we present a new approach based on a smoothed version of the distributional inclusion hypothesis. The new method is able to improve hypernym detection after testing on the BLESS dataset.

Ludovica Pannitto

NLP Lab Manager

NLP Lab Manager at Laboratorio Sperimentale (LILEC, Univeristy of Bologna).