Just as LHoTT subsumes quantum information formalisms, look to see what this does for NLP.
E.g., take ‘jokes of boys that Alice loves’ in terms of its dependency.
When does one want to keep elements completely separate, in different types, and when separated by a distance in a vector space? What is the total space of models of LHoTT?
Could there be a layer for grammatical sense and then one for meaningfulness with more refined typing? E.g., nvn, then person …
Urs Schreiber, Quantum Data Types via Linear Homotopy Type Theory (talk)
Bob Coecke, Giovanni de Felice, Konstantinos Meichanetzidis, Alexis Toumi, Foundations for Near-Term Quantum Natural Language Processing (arXiv:2012.03755)
Alexis Toumi, Category Theory for Quantum Natural Language Processing (arXiv:2212.06615)
Giovanni de Felice, Categorical Tools for Natural Language Processing (arXiv:2212.06636)
Last revised on March 10, 2023 at 17:13:35. See the history of this page for a list of all contributions to it.