A Study of Entanglement in a Categorical Framework of Natural Language

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 et al. [4] 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 t he lack of it) affects the compositional structures in practical situations. Our findings reveal tha t a number of proposals for verb construction lead to almost separable tensors, a fact that considerably s implifies the interactions between the words. We examine the ramifications of this fact, and we show t hat 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 lev el of entanglement.

[1]  Mehrnoosh Sadrzadeh,et al.  Lambek vs. Lambek: Functorial vector space semantics and string diagrams for Lambek calculus , 2013, Ann. Pure Appl. Log..

[2]  Stephen Clark,et al.  The Frobenius anatomy of word meanings I: subject and object relative pronouns , 2013, J. Log. Comput..

[3]  Stephen Clark,et al.  The Frobenius anatomy of word meanings II: possessive relative pronouns , 2014, J. Log. Comput..

[4]  G. M. Kelly.  Many-variable functorial calculus. I. , 1972 .

[5]  Stephen Clark,et al.  Mathematical Foundations for a Compositional Distributional Model of Meaning , 2010, ArXiv.

[6]  Mehrnoosh Sadrzadeh,et al.  Experimental Support for a Categorical Compositional Distributional Model of Meaning , 2011, EMNLP.

[7]  Anne Preller,et al.  Bell States and Negative Sentences in the Distributed Model of Meaning , 2011, Electron. Notes Theor. Comput. Sci..

[8]  Dimitri Kartsaklis,et al.  A Unified Sentence Space for Categorical Distributional-Compositional Semantics: Theory and Experiments , 2012, COLING.

[9]  Samson Abramsky,et al.  A categorical semantics of quantum protocols , 2004, Proceedings of the 19th Annual IEEE Symposium on Logic in Computer Science, 2004..

[10]  Dimitri Kartsaklis,et al.  Prior Disambiguation of Word Tensors for Constructing Sentence Vectors , 2013, EMNLP.

[11]  Mehrnoosh Sadrzadeh,et al.  Multi-Step Regression Learning for Compositional Distributional Semantics , 2013, IWCS.

[12]  Anne Preller,et al.  Free compact 2-categories , 2007, Mathematical Structures in Computer Science.

[13]  Mirella Lapata,et al.  Composition in Distributional Models of Semantics , 2010, Cogn. Sci..

[14]  Marco Baroni,et al.  Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space , 2010, EMNLP.

[15]  Dimitri Kartsaklis,et al.  Reasoning about Meaning in Natural Language with Compact Closed Categories and Frobenius Algebras , 2014, ArXiv.

[16]  T. Landauer,et al.  A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. , 1997 .

[17]  Silvia Bernardini,et al.  Introducing and evaluating ukWaC , a very large web-derived corpus of English , 2008 .

[18]  Hinrich Schütze,et al.  Automatic Word Sense Discrimination , 1998, Comput. Linguistics.

[19]  Hinrich Schütze,et al.  Introduction to information retrieval , 2008 .

[20]  Dimitri Kartsaklis,et al.  Resolving Lexical Ambiguity in Tensor Regression Models of Meaning , 2014, ACL.

[21]  Mehrnoosh Sadrzadeh,et al.  Experimenting with transitive verbs in a DisCoCat , 2011, GEMS.

[22]  Mehrnoosh Sadrzadeh,et al.  Concrete Models and Empirical Evaluations for the Categorical Compositional Distributional Model of Meaning , 2015, CL.

[23]  P. Selinger.  A Survey of Graphical Languages for Monoidal Categories , 2009, 0908.3347.