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

Nikos Athanasiou, Elias Iosif, Alexandros Potamianos


Abstract
Neural activation models have been proposed in the literature that use a set of example words for which fMRI measurements are available in order to find a mapping between word semantics and localized neural activations. Successful mappings let us expand to the full lexicon of concrete nouns using the assumption that similarity of meaning implies similar neural activation patterns. In this paper, we propose a computational model that estimates semantic similarity in the neural activation space and investigates the relative performance of this model for various natural language processing tasks. Despite the simplicity of the proposed model and the very small number of example words used to bootstrap it, the neural activation semantic model performs surprisingly well compared to state-of-the-art word embeddings. Specifically, the neural activation semantic model performs better than the state-of-the-art for the task of semantic similarity estimation between very similar or very dissimilar words, while performing well on other tasks such as entailment and word categorization. These are strong indications that neural activation semantic models can not only shed some light into human cognition but also contribute to computation models for certain tasks.
Anthology ID:
C18-1243
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2867–2878
Language:
URL:
https://aclanthology.org/C18-1243
DOI:
Bibkey:
Cite (ACL):
Nikos Athanasiou, Elias Iosif, and Alexandros Potamianos. 2018. Neural Activation Semantic Models: Computational lexical semantic models of localized neural activations. In Proceedings of the 27th International Conference on Computational Linguistics, pages 2867–2878, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Neural Activation Semantic Models: Computational lexical semantic models of localized neural activations (Athanasiou et al., COLING 2018)
Copy Citation:
PDF:
https://aclanthology.org/C18-1243.pdf
Code
 athn-nik/neural_asm
Data
SNLI