Distributional Sentence Entailment Using Density Matrices - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Distributional Sentence Entailment Using Density Matrices


Categorical compositional distributional model of Clark, Coecke, and Sadrzadeh 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.
Fichier principal
Vignette du fichier
385217_1_En_1_Chapter.pdf (250.45 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01446260 , version 1 (25-01-2017)





Esma Balkir, Mehrnoosh Sadrzadeh, Bob Coecke. Distributional Sentence Entailment Using Density Matrices. 1st International Conference on Theoretical Computer Science (TTCS), Aug 2015, Tehran, Iran. pp.1-22, ⟨10.1007/978-3-319-28678-5_1⟩. ⟨hal-01446260⟩
61 View
130 Download



Gmail Facebook X LinkedIn More