Default Handling in Incremental Generation
Karin Harbusch, Gen-ichiro Kikui, Anne Kilger
Abstract
Natural language generation must work with insufficient input. Underspecifications can be caused by shortcomings of the component providing the input or by the preliminary state of incrementally given input. The paper aims to escape from such dead-end situations by making assumptions. We discuss global aspects of default handling. Two problem classes for defaults in the incremental syntactic generator VM-GEN are presented to substantiate our discussion.
Create a lesson
Related papers
A Memory-Based Approach to Learning Shallow Natural Language Patterns
Shlomo Argamon, Ido Dagan, Yuval Krymolowski
A Comparison of WordNet and Roget's Taxonomy for Measuring Semantic Similarity
Michael Mc Hale
Some Ontological Principles for Designing Upper Level Lexical Resources
Nicola Guarino
Towards an implementable dependency grammar
Timo Jarvinen, Pasi Tapanainen
A Variant of Earley Parsing
Mark-Jan Nederhof, Giorgio Satta
Segregatory Coordination and Ellipsis in Text Generation
James Shaw