Neural Activation Semantic Models: Computational lexical semantic models of localized neural activations

by   Nikos Athanasiou, et al.

Neural activation models that have been proposed in the literature use a set of example wordsfor which fMRI measurements are available in order to find a mapping between word seman-tics and localized neural activations. Successful mappings let us expand to the full lexicon ofconcrete nouns using the assumption that similarity of meaning implies similar neural activationpatterns. In this paper, we propose a computational model that estimates semantic similarity inthe neural activation space and investigates the relative performance of this model for variousnatural language processing tasks. Despite the simplicity of the proposed model and the verysmall number of example words used to bootstrap it, the neural activation semantic model per-forms surprisingly well compared to state-of-the-art word embeddings. Specifically, the neuralactivation semantic model performs better than the state-of-the-art for the task of semantic simi-larity estimation between very similar or very dissimilar words, while performing well on othertasks such as entailment and word categorization. These are strong indications that neural acti-vation semantic models can not only shed some light into human cognition but also contribute tocomputation models for certain tasks.


page 1

page 2

page 3

page 4


fMRI Semantic Category Decoding using Linguistic Encoding of Word Embeddings

The dispute of how the human brain represents conceptual knowledge has b...

Affordance Extraction and Inference based on Semantic Role Labeling

Common-sense reasoning is becoming increasingly important for the advanc...

Utility of general and specific word embeddings for classifying translational stages of research

Conventional text classification models make a bag-of-words assumption r...

Word Embeddings Are Capable of Capturing Rhythmic Similarity of Words

Word embedding systems such as Word2Vec and GloVe are well-known in deep...

Mapping distributional to model-theoretic semantic spaces: a baseline

Word embeddings have been shown to be useful across state-of-the-art sys...

A Tale of Two Lexica Testing Computational Hypotheses with Deep Convolutional Neural Networks

Gow's (2012) dual lexicon model suggests that the primary purpose of wor...