How do people understand the meaning of the word small when used to describe a mosquito, a church, or a planet? While humans have a remarkable ability to form meanings by combining existing concepts, modeling this process is challenging. This paper addresses that challenge through CEREBRA (Context-dEpendent meaning REpresentations in the BRAin) neural network model. CEREBRA characterizes how word meanings dynamically adapt in the context of a sentence by decomposing sentence fMRI into words and words into embodied brain-based semantic features. It demonstrates that words in different contexts have different representations and the word meaning changes in a way that is meaningful to human subjects. CEREBRA’s context-based representations can potentially be used to make NLP applications more human-like.

PDF

In Proceedings of the Workshop on Semantic Spaces at the Intersection of NLP, Physics, and Cognitive Science , Groningen, Netherlands, June 2021.

@inproceedings{aguirre-celis:semspace2021, title={Understanding the Semantic Space: How Word Meanings Dynamically Adapt in the Context of a Sentence}, author={Nora Aguirre-Celis and Risto Miikkulainen}, booktitle={Proceedings of the Workshop on Semantic Spaces at the Intersection of NLP, Physics, and Cognitive Science }, month={June}, address={Groningen, Netherlands}, url="http://nn.cs.utexas.edu/?aguirre-celis:semspace2021", year={2021} }