News lunch mountains semantics

Semantics language

Abstract: Originally inspired by categorical quantum mechanics (Abramsky and Coecke, LiCS'04), the categorical compositional distributional model of natural language meaning of Coecke, Sadrzadeh and Clark provides a conceptually motivated procedure to compute the meaning of a sentence, given its grammatical structure within a Lambek pregroup and a vectorial representation of the meaning of its parts. The predictions of this first model have outperformed that of other models in mainstream empirical language processing tasks on large scale data. Moreover, just like CQM allows for varying the model in which we interpret quantum axioms, one can also vary the model in which we interpret word meaning.
In this paper we show that further developments in categorical quantum mechanics are relevant to natural language processing too. Firstly, Selinger's CPM-construction allows for explicitly taking into account lexical ambiguity and distinguishing between the two inherently different notions of homonymy and polysemy. In terms of the model in which we interpret word meaning, this means a passage from the vector space model to density matrices. Despite this change of model, standard empirical methods for comparing meanings can be easily adopted, which we demonstrate by a small-scale experiment on real-world data. This experiment moreover provides preliminary evidence of the validity of our proposed new model for word meaning.
Secondly, commutative classical structures as well as their non-commutative counterparts that arise in the image of the CPM-construction allow for encoding relative pronouns, verbs and adjectives, and finally, iteration of the CPM-construction, something that has no counterpart in the quantum realm, enables one to accommodate both entailment and ambiguity.
Subjects: Computation and Language (cs.CL); Logic in Computer Science (cs.LO); Category Theory (math.CT); Quantum Algebra (math.QA)
Cite as:
(or for this version)

Submission history

From: Robin Piedeleu [view email]

how much manager make why business ethics is important when london snow falls how much system 8 powerball who design central park roadmap what is agile how long project baseline results how much project management cost how many london boroughs which technology simulates higher order thinking when technology pushes the boundaries of art how much solution in vax platinum how often do entrepreneurs fail how many system restore points are kept how much product designer earn when manager mariah pitner who product registration which management approach is the best why technology is important who business analyst london who started the great fire what are the 5 levels of management how system calls work what london station goes to cambridge which solutions are isotonic how much start up capital do you need roadmap when to use what business can i start with 10k why technology is important in education teachers day when solution of nacl and agno3 are mixed which project runway designers are successful when teaching systems and routines to a group what is the solution process what is far in development how does roadmap work in jira how much phone 11 entrepreneur who create new ideas to whom project manager reports managing entrepreneur whose chief goal is where to find science articles why science is important for students how much manager's check bpi who science is it how far technology will go
You might also like
Demo Teaser - xMOF: A Semantics Specification Language for
Demo Teaser - xMOF: A Semantics Specification Language for ...
Cours de langue sur mesure : Semantics - The Art of Language
Cours de langue sur mesure : Semantics - The Art of Language
Unsupervised Bayesian Learning of Natural Language Semantics
Unsupervised Bayesian Learning of Natural Language Semantics
Related Posts