Paper: Learning Word-Class Lattices for Definition and Hypernym Extraction

ACL ID P10-1134
Title Learning Word-Class Lattices for Definition and Hypernym Extraction
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2010
Authors

Definition extraction is the task of au- tomatically identifying definitional sen- tences within texts. The task has proven useful in many research areas including ontology learning, relation extraction and question answering. However, current ap- proaches – mostly focused on lexico- syntactic patterns – suffer from both low recall and precision, as definitional sen- tences occur in highly variable syntactic structures. In this paper, we propose Word- Class Lattices (WCLs), a generalization of word lattices that we use to model tex- tual definitions. Lattices are learned from a dataset of definitions from Wikipedia. Our method is applied to the task of def- inition and hypernym extraction and com- pares favorably to other pattern general- ization methods proposed in the literature.