Distributional sentence entailment using density matrices

DOI10.1007/978-3-319-28678-5_1MaRDI QIDQ2798016zbMATH OpenOpenAlexFDO

Authors Esma Balkır, Mehrnoosh Sadrzadeh, Bob Coecke

Publication date 1 April 2016

Published in Topics in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1506.06534

Mathematics Subject Classification ID

Logic of natural languages (03B65) Natural language processing (68T50)

Abstract: Categorical compositional distributional model of Coecke et al. (2010) suggests a way to combine grammatical composition of the formal, type logical models with the corpus based, empirical word representations of distributional semantics. This paper contributes to the project by expanding the model to also capture entailment relations. This is achieved by extending the representations of words from points in meaning space to density operators, which are probability distributions on the subspaces of the space. A symmetric measure of similarity and an asymmetric measure of entailment is defined, where lexical entailment is measured using von Neumann entropy, the quantum variant of Kullback-Leibler divergence. Lexical entailment, combined with the composition map on word representations, provides a method to obtain entailment relations on the level of sentences. Truth theoretic and corpus-based examples are provided.

Recommendations

• Sentence entailment in compositional distributional semantics
• Semantic composition inspired by quantum measurement
• Open system categorical quantum semantics in natural language processing
• Towards logical negation for compositional distributional semantics
• A Compositional Distributional Inclusion Hypothesis

Cited in

(15)

• Distributional formal semantics
• Semantic composition inspired by quantum measurement
• Bell states and negative sentences in the distributed model of meaning
• Double dilation double mixing (extended abstract)
• Higher-order CPM constructions
• From logical to distributional models
• The Mathematics of Text Structure
• Language modeling with reduced densities
• Open system categorical quantum semantics in natural language processing
• Towards logical negation for compositional distributional semantics
• Density matrices with metric for derivational ambiguity
• Composing conversational negation
• Concrete sentence spaces for compositional distributional models of meaning
• Density matrices for metaphor understanding
• Sentence entailment in compositional distributional semantics

This page was built for publication: Distributional sentence entailment using density matrices

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2798016)