A Vector Field Approach to Lexical Semantics
2014 (English)Conference paper (Refereed)
We report work in progress on measuring "forces" underlying the semantic drift by comparing it with plate tectonics in geology. Based on a brief survey of energy as a key concept in machine learning, and the Aristotelian concept of potentiality vs. actuality allowing for the study of energy and dynamics in language, we propose a field approach to lexical analysis. Until evidence to the contrary, it was assumed that a classical field in physics is appropriate to model word semantics. The approach used the distributional hypothesis to statistically model word meaning. We do not address the modelling of sentence meaning here. The computability of a vector field for the indexing vocabulary of the Reuters-21578 test collection by an emergent self-organizing map suggests that energy minima as learnables in machine learning presuppose concepts as energy minima in cognition. Our finding needs to be confirmed by a systematic evaluation.
Place, publisher, year, edition, pages
Springer , 2014.
distributional semantics, vector fields, Computational Linguistics
Research subject Library and Information Science
IdentifiersURN: urn:nbn:se:hb:diva-7199Local ID: 2320/13809OAI: oai:DiVA.org:hb-7199DiVA: diva2:887907
8th International Conference on Quantum Interaction, Filzbach, Switzerland. June 30 - July 3, 2014
European Commission Seventh Framework Programme under Grant Agreement Number FP7-601138 PERICLES2015-12-222015-12-22