Functional Distributional Semantics
Vector space models have become popular in distributional semantics, despite the challenges they face in capturing various semantic phenomena. We propose a novel probabilistic framework which draws on both formal semantics and recent advances in machine learning. In particular, we separate predicates from the entities they refer to, allowing us to perform Bayesian inference based on logical forms. We describe an implementation of this framework using a combination of Restricted Boltzmann Machines and feedforward neural networks. Finally, we demonstrate the feasibility of this approach by training it on a parsed corpus and evaluating it on established similarity datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian InferenceBIG-bench Machine LearningSimilar Papers 제목 키워드 기반
Learning Functional Distributional Semantics with Visual Data
Functional Distributional Semantics is a recently proposed framework for learning distributional semantics that provides linguistic interpretability. It models the meaning of a word as a binary classifier rather than a n…
Language AcquisitionLearning Functional Distributional Semantics with Visual Data
Functional Distributional Semantics is a recently proposed framework for learning distributional semantics that provides linguistic interpretability. It models the meaning of a word as a binary classifier rather than a n…
Language AcquisitionAutoencoding Pixies: Amortised Variational Inference with Graph Convolutions for Functional Distributional Semantics
Functional Distributional Semantics provides a linguistically interpretable framework for distributional semantics, by representing the meaning of a word as a function (a binary classifier), instead of a vector. However,…
Language ModelingLanguage ModellingSemantic CompositionSemantic Similarity+2Distributional Inclusion Hypothesis and Quantifications: Probing for Hypernymy in Functional Distributional Semantics
Functional Distributional Semantics (FDS) models the meaning of words by truth-conditional functions. This provides a natural representation for hypernymy but no guarantee that it can be learnt when FDS models are traine…
Linguists Who Use Probabilistic Models Love Them: Quantification in Functional Distributional Semantics
Functional Distributional Semantics provides a computationally tractable framework for learning truth-conditional semantics from a corpus. Previous work in this framework has provided a probabilistic version of first-ord…
Bayesian Inference