Towards knowledge about causal agents in wordnet

Authors:
David B. Bracewell;Fuji Ren;Shingo Kuroiwa
Affiliations:
Department of Information Science and Intelligent Systems, The University of Tokushima, Tokushima-shi, Tokushima-ken, Japan;Department of Information Science and Intelligent Systems, The University of Tokushima, Tokushima-shi, Tokushima-ken, Japan and School of Information Engineering, Beijing University of Posts and T ...;Department of Information Science and Intelligent Systems, The University of Tokushima, Tokushima-shi, Tokushima-ken, Japan
Venue:
ICCOMP'06 Proceedings of the 10th WSEAS international conference on Computers
Year:
2006

Citing 4
Cited 0

Enriching the WordNet taxonomy with contextual knowledge acquired from text

Natural language processing and knowledge representation
Accurate Semantic Annotations via Pattern Matching

Proceedings of the Fifteenth International Florida Artificial Intelligence Research Society Conference
Building a large annotated corpus of English: the penn treebank

Computational Linguistics - Special issue on using large corpora: II
WordNet: similarity - measuring the relatedness of concepts

AAAI'04 Proceedings of the 19th national conference on Artifical intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

WordNet is widely used in Natural Language Processing (NLP). It however lacks certain information, such as functions and attributes for nouns. In this paper a method for obtaining this knowledge from the glosses for a subset of causal agents is given. This extra knowledge can help in Question & Answering, Machine Translation, etc. Different classes of glasses were created and based on these classes we attempt to gain knowledge in a frame-based representation about actions, attributes, and domains.