Feature2Vec: Distributional semantic modelling of human property knowledge

TL;DR

Feature2Vec is a novel method that maps human property knowledge onto a distributional semantic space, enabling interpretable and efficient modeling of word features and improving over previous approaches.

Contribution

We adapt the word2vec architecture to model human-like concept features within a distributional semantic space, enhancing interpretability and ranking of semantic properties.

Findings

Our model outperforms previous approaches on evaluation tasks.

It provides a measure of concept-feature affinity in a single space.

The method facilitates extension of feature norm datasets.

Abstract

Feature norm datasets of human conceptual knowledge, collected in surveys of human volunteers, yield highly interpretable models of word meaning and play an important role in neurolinguistic research on semantic cognition. However, these datasets are limited in size due to practical obstacles associated with exhaustively listing properties for a large number of words. In contrast, the development of distributional modelling techniques and the availability of vast text corpora have allowed researchers to construct effective vector space models of word meaning over large lexicons. However, this comes at the cost of interpretable, human-like information about word meaning. We propose a method for mapping human property knowledge onto a distributional semantic space, which adapts the word2vec architecture to the task of modelling concept features. Our approach gives a measure of concept and feature affinity in a single semantic space, which makes for easy and efficient ranking of candidate human-derived semantic properties for arbitrary words. We compare our model with a previous approach, and show that it performs better on several evaluation tasks. Finally, we discuss how our method could be used to develop efficient sampling techniques to extend existing feature norm datasets in a reliable way.