Towards Compositional Distributional Discourse Analysis

Bob Coecke
(University of Oxford)
Giovanni de Felice
(University of Oxford)
Dan Marsden
(University of Oxford)
Alexis Toumi
(University of Oxford)

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.

In Martha Lewis, Bob Coecke, Jules Hedges, Dimitri Kartsaklis and Dan Marsden: Proceedings of the 2018 Workshop on Compositional Approaches in Physics, NLP, and Social Sciences (CAPNS 2018), Nice, France, 2-3rd September 2018, Electronic Proceedings in Theoretical Computer Science 283, pp. 1–12.
Published: 8th November 2018.

ArXived at: https://dx.doi.org/10.4204/EPTCS.283.1 bibtex PDF
References in reconstructed bibtex, XML and HTML format (approximated).
Comments and questions to: eptcs@eptcs.org
For website issues: webmaster@eptcs.org