Graded Entailment for Compositional Distributional Semantics
Desislava Bankova, Bob Coecke, Martha Lewis, Daniel Marsden

TL;DR
This paper introduces a novel graded entailment framework within categorical compositional distributional semantics, enabling the measurement of entailment strength between concepts and sentences using density matrices and quantum logic principles.
Contribution
It develops a new model of lexical and sentence entailment using density matrices and categorical semantics, extending compositional distributional semantics with graded entailment measures.
Findings
Entailment strength can be computed using density matrices.
Entailment lifts compositionally to the sentence level, providing lower bounds.
Quantum logic is embedded in the graded order for entailment analysis.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputability, Logic, AI Algorithms · Topic Modeling · Quantum Computing Algorithms and Architecture
