Graded Entailment for Compositional Distributional Semantics

01/19/2016
by   Desislava Bankova, et al.
0

The categorical compositional distributional model of natural language provides a conceptually motivated procedure to compute the meaning of sentences, given grammatical structure and the meanings of its words. This approach has outperformed other models in mainstream empirical language processing tasks. However, until recently it has lacked the crucial feature of lexical entailment -- as do other distributional models of meaning. In this paper we solve the problem of entailment for categorical compositional distributional semantics. Taking advantage of the abstract categorical framework allows us to vary our choice of model. This enables the introduction of a notion of entailment, exploiting ideas from the categorical semantics of partial knowledge in quantum computation. The new model of language uses density matrices, on which we introduce a novel robust graded order capturing the entailment strength between concepts. This graded measure emerges from a general framework for approximate entailment, induced by any commutative monoid. Quantum logic embeds in our graded order. Our main theorem shows that entailment strength lifts compositionally to the sentence level, giving a lower bound on sentence entailment. We describe the essential properties of graded entailment such as continuity, and provide a procedure for calculating entailment strength.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/14/2015

Sentence Entailment in Compositional Distributional Semantics

Distributional semantic models provide vector representations for words ...
research
06/22/2015

Distributional Sentence Entailment Using Density Matrices

Categorical compositional distributional model of Coecke et al. (2010) s...
research
02/03/2015

Open System Categorical Quantum Semantics in Natural Language Processing

Originally inspired by categorical quantum mechanics (Abramsky and Coeck...
research
02/13/2013

Entailment in Probability of Thresholded Generalizations

A nonmonotonic logic of thresholded generalizations is presented. Given ...
research
05/12/2021

Conversational Negation using Worldly Context in Compositional Distributional Semantics

We propose a framework to model an operational conversational negation b...
research
08/04/2016

Entailment Relations on Distributions

In this paper we give an overview of partial orders on the space of prob...
research
07/10/2012

Challenges for Distributional Compositional Semantics

This paper summarises the current state-of-the art in the study of compo...

Please sign up or login with your details

Forgot password? Click here to reset