Towards Compositional Distributional Discourse Analysis

Categorical compositional distributional semantics provide a method to derive the meaning of a sentence from the meaning of its individual words: the grammatical reduction of a sentence automatically induces a linear map for composing the word vectors obtained from distributional semantics. In this paper, we extend this passage from word-to-sentence to sentence-to-discourse composition. To achieve this we introduce a notion of basic anaphoric discourses as a mid-level representation between natural language discourse formalised in terms of basic discourse representation structures (DRS); and knowledge base queries over the Semantic Web as described by basic graph patterns in the Resource Description Framework (RDF). This provides a high-level specification for compositional algorithms for question answering and anaphora resolution, and allows us to give a picture of natural language understanding as a process involving both statistical and logical resources.

[1]  Bob Coecke,et al.  Interacting quantum observables: categorical algebra and diagrammatics , 2009, ArXiv.

[2]  Guillaume Bouchard,et al.  Knowledge Graph Completion via Complex Tensor Factorization , 2017, J. Mach. Learn. Res..

[3]  Bob Coecke,et al.  New Structures for Physics , 2011 .

[4]  Li Deng,et al.  Question-Answering with Grammatically-Interpretable Representations , 2017, AAAI.

[5]  Anne Preller,et al.  From Natural Language to RDF Graphs with Pregroups , 2014, EACL 2014.

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

[7]  Aleks Kissinger,et al.  Picturing Quantum Processes: A First Course in Quantum Theory and Diagrammatic Reasoning , 2017 .

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

[9]  S. Clark,et al.  A Compositional Distributional Model of Meaning , 2008 .

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

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

[12]  Stephen Clark,et al.  A quantum teleportation inspired algorithm produces sentence meaning from word meaning and grammatical structure , 2013, ArXiv.

[13]  Boris Motik,et al.  Estimating the Cardinality of Conjunctive Queries over RDF Data Using Graph Summarisation , 2018, WWW.

[14]  Samson Abramsky,et al.  Contextual Semantics: From Quantum Mechanics to Logic, Databases, Constraints, and Complexity , 2014, Bull. EATCS.

[15]  B. Coecke,et al.  Categories for the practising physicist , 2009, 0905.3010.

[16]  Paul Smolensky,et al.  Connectionist AI, symbolic AI, and the brain , 1987, Artificial Intelligence Review.

[17]  Samson Abramsky,et al.  Semantic Unification A sheaf theoretic approach to natural language , 2014, Categories and Types in Logic, Language, and Physics.

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

[19]  Uwe Reyle,et al.  From Discourse to Logic - Introduction to Modeltheoretic Semantics of Natural Language, Formal Logic and Discourse Representation Theory , 1993, Studies in linguistics and philosophy.

[20]  Martha Lewis,et al.  Generalized relations in linguistics & cognition , 2018, Theor. Comput. Sci..