Variational Inference for Logical Inference
Accepted version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Emerson, Guy https://orcid.org/0000-0002-3136-9682
Copestake, Ann https://orcid.org/0000-0003-0347-946X
Abstract
Functional Distributional Semantics is a framework that aims to learn, from text, semantic representations which can be interpreted in terms of truth. Here we make two contributions to this framework. The first is to show how a type of logical inference can be performed by evaluating conditional probabilities. The second is to make these calculations tractable by means of a variational approximation. This approximation also enables faster convergence during training, allowing us to close the gap with state-of-the-art vector space models when evaluating on semantic similarity. We demonstrate promising performance on two tasks.
Description
Keywords
cs.CL, cs.CL
Journal Title
CoRR
Conference Name
The 2017 Conference on Logic and Machine Learning for Natural Language
Journal ISSN
2002-9764
Volume Title
Publisher
University of Gothenburg
Publisher DOI
Sponsorship
Schiff Foundation