Feature2Vec: Distributional semantic modelling of human property knowledge
This work addresses the problem of limited interpretable semantic data for neurolinguistic research by enabling efficient ranking of human-derived properties for arbitrary words, though it is incremental as it builds on existing distributional modeling techniques.
The paper tackled the limitation of small feature norm datasets for modeling human conceptual knowledge by mapping human property knowledge onto a distributional semantic space using an adapted word2vec architecture, resulting in better performance on evaluation tasks compared to a previous approach.
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.