A Study of Entanglement in a Categorical Framework of Natural Language
arXiv:1405.2874 · doi:10.4204/EPTCS.172.17
Abstract
In both quantum mechanics and corpus linguistics based on vector spaces, the notion of entanglement provides a means for the various subsystems to communicate with each other. In this paper we examine a number of implementations of the categorical framework of Coecke, Sadrzadeh and Clark (2010) for natural language, from an entanglement perspective. Specifically, our goal is to better understand in what way the level of entanglement of the relational tensors (or the lack of it) affects the compositional structures in practical situations. Our findings reveal that a number of proposals for verb construction lead to almost separable tensors, a fact that considerably simplifies the interactions between the words. We examine the ramifications of this fact, and we show that the use of Frobenius algebras mitigates the potential problems to a great extent. Finally, we briefly examine a machine learning method that creates verb tensors exhibiting a sufficient level of entanglement.
arXiv commentIn Proceedings QPL 2014, arXiv:1412.8102
References in corpus (5)
- Experimental Support for a Categorical Compositional Distributional Model of Meaning
- The Frobenius anatomy of word meanings I: subject and object relative pronouns
- Lambek vs. Lambek: Functorial Vector Space Semantics and String Diagrams for Lambek Calculus
- Experimenting with Transitive Verbs in a DisCoCat
- The Frobenius anatomy of word meanings II: possessive relative pronouns
Cited by in corpus (19)
- QNLP in Practice: Running Compositional Models of Meaning on a Quantum Computer
- Quantum Natural Language Processing on Near-Term Quantum Computers
- Quantum Language Model with Entanglement Embedding for Question Answering
- Foundations for Near-Term Quantum Natural Language Processing
- Quantum Mathematics in Artificial Intelligence
- Evaluating Neural Word Representations in Tensor-Based Compositional Settings
- Autonomization of Monoidal Categories
- Using Sentence Plausibility to Learn the Semantics of Transitive Verbs
- Meaning updating of density matrices
- Distributional Inclusion Hypothesis for Tensor-based Composition
- PromptCL: Improving Event Representation via Prompt Template and Contrastive Learning
- Uniqueness of Composition in Quantum Theory and Linguistics
- Event Representation Learning Enhanced with External Commonsense Knowledge
- Learning Semantically and Additively Compositional Distributional Representations
- Talking Space: inference from spatial linguistic meanings
- Internal Wiring of Cartesian Verbs and Prepositions
- One Representation per Word - Does it make Sense for Composition?
- A Factorized Model for Transitive Verbs in Compositional Distributional Semantics
- Collaborative Training of Tensors for Compositional Distributional Semantics