Representing and resolving ambiguities in ontology-based question answering

Authors:
Christina Unger;Philipp Cimiano
Affiliations:
Universität Bielefeld, Germany;Universität Bielefeld, Germany
Venue:
TIWTE '11 Proceedings of the TextInfer 2011 Workshop on Textual Entailment
Year:
2011

Citing 7
Cited 0

Mathematical and computational aspects of lexicalized grammars

Mathematical and computational aspects of lexicalized grammars
Learning language semantics from ambiguous supervision

AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
Learning context-dependent mappings from sentences to logical form

ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2
Flexible semantic composition with DUDES

IWCS-8 '09 Proceedings of the Eighth International Conference on Computational Semantics
Pythia: compositional meaning construction for ontology-based question answering on the semantic web

NLDB'11 Proceedings of the 16th international conference on Natural language processing and information systems
Natural language interfaces: what is the problem? – a data-driven quantitative analysis

NLDB'09 Proceedings of the 14th international conference on Applications of Natural Language to Information Systems
Natural language interfaces to ontologies: combining syntactic analysis and ontology-based lookup through the user interaction

ESWC'10 Proceedings of the 7th international conference on The Semantic Web: research and Applications - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Ambiguities are ubiquitous in natural language and pose a major challenge for the automatic interpretation of natural language expressions. In this paper we focus on different types of lexical ambiguities that play a role in the context of ontology-based question answering, and explore strategies for capturing and resolving them. We show that by employing underspecification techniques and by using ontological reasoning in order to filter out inconsistent interpretations as early as possible, the overall number of interpretations can be effectively reduced by 44 %.