Towards Compositional Distributional Discourse Analysis
This work addresses natural language understanding by integrating statistical and logical methods, though it appears incremental as it builds on existing compositional semantics.
The paper tackles the problem of extending compositional distributional semantics from sentences to discourse by introducing basic anaphoric discourses as a mid-level representation, enabling high-level specifications for algorithms in question answering and anaphora resolution.
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.