Classifying Non-Sentential Utterances in Dialogue: A Machine Learning Approach
Computational Linguistics
Towards a Context Theory for Context-aware systems
Proceedings of the 2007 conference on Advances in Ambient Intelligence
Goal reasoning with context record types
CONTEXT'07 Proceedings of the 6th international and interdisciplinary conference on Modeling and using context
Modeling Contexts with Dependent Types
Fundamenta Informaticae
| Hi-index | 0.00 |
The paper develops a semantics for natural language interrogatives which identifies questions---the denotations of interrogatives---with propositional abstracts. The paper argues that a theory of Questions as Propositional Abstracts (QPA), is a simple, transparently implementable theory that has significant empirical coverage. However, until recently QPA has been abandoned in formal semantic treatments of questions, due to a number of significant problems QPA encountered when formulated within the type system of Montague Semantics. In recent work, Ginzburg and Sag provided a a situation theoretic implementation of QPA that succeeded in overcoming certain of the original problems for QPA. However, Ginzburg and Sag's proposal relied on a special purpose account of λ-abstraction, raising the question to what extent QPA can be sustained using standard notions of abstraction. In this paper such doubts are allayed by implementing QPA in a version of Type Theory that provides record types. These latter allow one to develop notions of simultaneous/vacuous abstraction with restrictions and an ontology with various 'informational entities'. Moreover, the intrinsic polymorphism of this theory plays a crucial role in enabling the definition of a general type for questions, one of the main stumbling blocks for earlier versions of QPA.