Author:
Bankova Dea,Coecke Bob,Lewis Martha,Marsden Dan
Abstract
The categorical compositional distributional model of natural language provides a conceptually motivated procedure to compute the meaning of a sentence, given its grammatical structure and the meanings of its words. This approach has outperformed other models in mainstream empirical language processing tasks, but lacks an effective model of lexical entailment. We address this shortcoming by exploiting the freedom in our abstract categorical framework to change our choice of semantic model. This allows us to describe hyponymy as a graded order on meanings, using models of partial information used in quantum computation. Quantum logic embeds in this graded order.
Publisher
Institute of Computer Science, Polish Academy of Sciences
Subject
Computer Science Applications,Linguistics and Language,Modeling and Simulation
Cited by
10 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Density Matrices for Metaphor Understanding;Electronic Proceedings in Theoretical Computer Science;2024-08-12
2. Adapting the DisCoCat-Model for Question Answering in the Chinese Language;2023 IEEE International Conference on Quantum Computing and Engineering (QCE);2023-09-17
3. Sentence Classification Using Quantum Natural Language Processing and Comparison of Optimization Methods;Communications in Computer and Information Science;2023
4. Composing Conversational Negation;Electronic Proceedings in Theoretical Computer Science;2022-11-03
5. Quantum computations for disambiguation and question answering;Quantum Information Processing;2022-03-30