Context-theoretic Semantics for Natural Language: an Algebraic Framework

no code implementations • 22 Sep 2020 • Daoud Clarke

The meaning of a string of words is assumed to be a vector representing the contexts it occurs in in the corpus model.

Natural Language Inference

Algorithms and Architecture for Real-time Recommendations at News UK

no code implementations • 15 Sep 2017 • Dion Bailey, Tom Pajak, Daoud Clarke, Carlos Rodriguez

At News UK, there is a requirement to be able to quickly generate recommendations for users on news items as they are published.

Collaborative Filtering Recommendation Systems

Simple, Fast Semantic Parsing with a Tensor Kernel

no code implementations • 2 Jul 2015 • Daoud Clarke

We describe a simple approach to semantic parsing based on a tensor product kernel.

Semantic Parsing

Efficiency in Ambiguity: Two Models of Probabilistic Semantics for Natural Language

no code implementations • WS 2015 • Daoud Clarke, Bill Keller

Coreference Resolution Learning Semantic Representations +3

Riesz Logic

no code implementations • 10 Oct 2014 • Daoud Clarke

We introduce Riesz Logic, whose models are abelian lattice ordered groups, which generalise Riesz spaces (vector lattices), and show soundness and completeness.

Learning to Distinguish Hypernyms and Co-Hyponyms

1 code implementation • COLING 2014 • Julie Weeds, Daoud Clarke, Jeremy Reffin, David Weir, Bill Keller

Natural Language Inference Semantic Textual Similarity +1

A Context-Theoretic Framework for Compositionality in Distributional Semantics

no code implementations • CL 2012 • Daoud Clarke

Natural Language Inference