CogALex-V Shared Task: ROOT18

TL;DR

This paper presents ROOT 18, a classifier that uses distributional measures to identify semantic relations between words, performing well on relatedness detection but less effectively on relation classification.

Contribution

It introduces a classifier leveraging multiple distributional measures for semantic relation classification, highlighting limitations in distinguishing multiple relations simultaneously.

Findings

High accuracy in relatedness detection

Poor performance in relation classification

Distributional measures insufficient for multiple relation discrimination

Abstract

In this paper, we describe ROOT 18, a classifier using the scores of several unsupervised distributional measures as features to discriminate between semantically related and unrelated words, and then to classify the related pairs according to their semantic relation (i.e. synonymy, antonymy, hypernymy, part-whole meronymy). Our classifier participated in the CogALex-V Shared Task, showing a solid performance on the first subtask, but a poor performance on the second subtask. The low scores reported on the second subtask suggest that distributional measures are not sufficient to discriminate between multiple semantic relations at once.