Abstract
A Support Vector Machines (SVM) classifier of FrameNet semantic roles was implemented based on a set of new and previously used syntactic and semantic features. At Senseval 3, the system achieved a precision of 0.807 for the restricted test and 0.898 for the non-restricted test.
| Original language | English (US) |
|---|---|
| Pages | 167-170 |
| Number of pages | 4 |
| State | Published - 2004 |
| Externally published | Yes |
| Event | 3rd International Workshop on the Evaluation of Systems for the Semantic Analysis of Text, SENSEVAL@ACL 2004 - Barcelona, Spain Duration: Jul 25 2004 → Jul 26 2004 |
Conference
| Conference | 3rd International Workshop on the Evaluation of Systems for the Semantic Analysis of Text, SENSEVAL@ACL 2004 |
|---|---|
| Country/Territory | Spain |
| City | Barcelona |
| Period | 7/25/04 → 7/26/04 |
ASJC Scopus subject areas
- Control and Systems Engineering