Towards Compositional Distributional Discourse Analysis

Abstract

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 Proceedings CAPNS 2018, arXiv:1811.02701

References in corpus (6)

• Interacting Quantum Observables: Categorical Algebra and Diagrammatics
• A survey of graphical languages for monoidal categories
• Mathematical Foundations for a Compositional Distributional Model of Meaning
• The Frobenius anatomy of word meanings I: subject and object relative pronouns
• The Frobenius anatomy of word meanings II: possessive relative pronouns
• Estimating the Cardinality of Conjunctive Queries over RDF Data Using Graph Summarisation

Cited by in corpus (3)

• DisCoPy: Monoidal Categories in Python
• Functorial Question Answering
• Functorial Language Games for Question Answering