A Neurobiologically Motivated Analysis of Distributional Semantic Models

AbstractThe pervasive use of distributional semantic models or word embeddings is due to their remarkable ability to represent the meanings of words for both practical application and cognitive modeling. However, little has been known about what kind of information is encoded in text-based word vectors. This lack of understanding is particularly problematic when distributional semantics is regarded as a model of semantic representation for abstract concepts. This paper attempts to reveal the internal knowledge encoded in distributional word vectors by the analysis using Binder et al.'s (2016) brain-based vectors, explicitly structured conceptual representations based on neurobiologically motivated attributes. In the analysis, the mapping from text-based vectors to brain-based vectors is trained and prediction performance is evaluated by comparing the estimated and original brain-based vectors. The analysis demonstrates that social and cognitive information is predicted with the highest accuracy by text-based vectors, but emotional information is not predicted so accurately. This result is discussed in terms of embodied theories for abstract concepts.


Return to previous page