Abstract | ||
---|---|---|
This paper discusses our contribution to the third RTE Challenge -- the SALSA RTE system. It builds on an earlier system based on a relatively deep linguistic analysis, which we complement with a shallow component based on word overlap. We evaluate their (combined) performance on various data sets. However, earlier observations that the combination of features improves the overall accuracy could be replicated only partly. |
Year | Venue | Keywords |
---|---|---|
2007 | ACL-PASCAL@ACL | overall accuracy,earlier system,shallow component,semantic approach,various data set,system evaluation,salsa rte system,task analysis,earlier observation,rte challenge,deep linguistic analysis |
Field | DocType | Volume |
Data set,Textual entailment,Task analysis,Computer science,System evaluation,Natural language processing,Artificial intelligence,Linguistic analysis | Conference | W07-14 |
Citations | PageRank | References |
16 | 0.94 | 3 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Aljoscha Burchardt | 1 | 188 | 18.51 |
Nils Reiter | 2 | 37 | 7.69 |
Stefan Thater | 3 | 756 | 38.54 |
Anette Frank | 4 | 32 | 4.70 |