This study proposes to employ syntactic and semantic knowledge from the rich relations within a tree kernel structure for relation extraction. The underlying idea is that different tree kernels with a variety of representations of the available linguistic information will improve the performance of detecting useful pieces of information expressed in a sentence. Applying clause-based rules, clustering algorithms, and bootstrapping on them will help increase the performance of relation extraction. As outlined in this paper, we plan to conduct experiments on recent Information Extraction corpuses and compare the results with the state of the art.
Author and article information
Laboratory for Systems, Software and Semantics (LS
Ryerson University, Toronto, ON, Canada