How Well Do Distributional Models Capture Different Types of Semantic Knowledge?

Dana Rubinstein, Effi Levi, Roy Schwartz, Ari Rappoport

2015 · 81 citations · 18 references

DOIFull text

Open access

Concepts

Abstract

In recent years, distributional models (DMs) have shown great success in repre-senting lexical semantics. In this work we show that the extent to which DMs rep-resent semantic knowledge is highly de-pendent on the type of knowledge. We pose the task of predicting properties of concrete nouns in a supervised setting, and compare between learning taxonomic properties (e.g., animacy) and attributive properties (e.g., size, color). We employ four state-of-the-art DMs as sources of feature representation for this task, and show that they all yield poor results when tested on attributive properties, achieving no more than an average F-score of 0.37 in the binary property prediction task, com-pared to 0.73 on taxonomic properties. Our results suggest that the distributional hypothesis may not be equally applicable to all types of semantic information. 1

References

18