Header logo is

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

2018

Conference Paper


Neural activation models that have been proposed in the literature 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.

Author(s): Nikos Athanasiou and Elias Iosif and Alexandros Potamianos
Book Title: International Conference on Computational Linguistics (COLING)
Year: 2018
Month: August

Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Event Place: Santa Fe, New Mexico, USA
Attachments: pdf

BibTex

@inproceedings{NASM:Coling18,
  title = {Neural Activation Semantic Models: Computational lexical semantic models of localized neural activations},
  author = {Athanasiou, Nikos and Iosif, Elias and Potamianos, Alexandros},
  booktitle = {International Conference on Computational Linguistics (COLING) },
  month = aug,
  year = {2018},
  doi = {},
  month_numeric = {8}
}