Abstract | ||
---|---|---|
To score well in RTE3, and even more so to create good justifications for entailments, substantial lexical and world knowledge is needed. With this in mind, we present an analysis of a sample of the RTE3 positive entailment pairs, to identify where and what kinds of world knowledge are needed to fully identify and justify the entailment, and discuss several existing resources and their capacity for supplying that knowledge. We also briefly sketch the path we are following to build an RTE system (Our implementation is very preliminary, scoring 50.9% at the time of RTE). The contribution of this paper is thus a framework for discussing the knowledge requirements posed by RTE and some exploration of how these requirements can be met. |
Year | Venue | Keywords |
---|---|---|
2007 | ACL-PASCAL@ACL | world knowledge,substantial lexical,rte3 positive entailment pair,rte system,existing resource,good justification,knowledge requirement |
Field | DocType | Citations |
Logical consequence,Computer science,Artificial intelligence,Natural language processing,Machine learning,Sketch | Conference | 24 |
PageRank | References | Authors |
1.57 | 2 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Peter Clark | 1 | 780 | 72.67 |
William R. Murray | 2 | 40 | 3.60 |
John Thompson | 3 | 188 | 16.34 |
Phil Harrison | 4 | 124 | 10.29 |
Jerry R. Hobbs | 5 | 2337 | 553.71 |
Christiane Fellbaum | 6 | 444 | 45.56 |