Functorial Language Models
We introduce functorial language models: a principled way to compute probability distributions over word sequences given a monoidal functor from grammar to meaning. This yields a method for training categorical compositional distributional (DisCoCat) models on raw text data. We provide a proof-of-concept implementation in DisCoPy, the Python toolbox for monoidal categories.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Functorial Hierarchical Clustering with Overlaps
This work draws inspiration from three important sources of research on dissimilarity-based clustering and intertwines those three threads into a consistent principled functorial theory of clustering. Those three are the…
ClusteringFunctorial Language Games for Question Answering
We present some categorical investigations into Wittgenstein's language-games, with applications to game-theoretic pragmatics and question-answering in natural language processing.
Question AnsweringFunctorial Neural Architectures from Higher Inductive Types
Neural networks often learn the parts of a task but fail on novel combinations of those parts. We argue that this failure is architectural: a decoder generalizes compositionally only when it respects the algebraic laws o…
Classifying Clustering Schemes
Many clustering schemes are defined by optimizing an objective function defined on the partitions of the underlying set of a finite metric space. In this paper, we construct a framework for studying what happens when we …
ClusteringFunctorial Manifold Learning
We adapt previous research on category theory and topological unsupervised learning to develop a functorial perspective on manifold learning. We first characterize manifold learning algorithms as functors that map pseudo…
Clustering