Semantic Spaces at the Intersection of NLP, Physics, and Cognitive Science.
Martha Lewis, Dan Marsden, Mehrnoosh Sadrzadeh · UvA-DARE (University of Amsterdam) · 2020
The ability to compose parts to form a more complex whole, and to analyze a whole as a combination of elements, is desirable across disciplines. Semantic Spaces at the Intersection of Natural Language Processing (NLP), Physics, and Cognitive Science brought together researchers applying similar compositional approaches within the three disciplines. The categorical model of [6], inspired by quantum protocols, has provided a convincing account of compositionality in vector space models of NLP. Similar category-theoretic approaches have been applied in cognitive science, in the context of conceptual spaces. The interplay between the three disciplines fostered theoretically motivated approaches to understanding how meanings of words interact in sentences and discourse, and how concepts develop in a cognitive space. This volume sees commonalities between the compositional mechanisms employed extracted, and applications and phenomena traditionally thought of as ‘non-compositional’ being shown to be compositional.