Authors:
 Mihai Surdeanu

 

 

Description:
 SwiRL is a Semantic Role Labeling (SRL) system for English constructed on top of the full syntactic analysis of text. Achieved state-of-the-art performance in the CoNLL 2005 SRL evaluation.

 

Functionality:

 

Technology:
 C++

 

Technical Requirements:
 Charniak Parser (included), Xavi Carreras' AdaBoost library (included).

Modules:

  • Semantic Role Labeler

 

Innovation:
 It has state-of-the-art performance: currently its F1 on the WSJ corpus is 77+, and on the Brown corpus it is 66+ points. SwiRL ranks fifth among the systems that participated at the CoNLL 2005 shared task evaluation, but all the systems that scored higher were actually combinations of several individual models.

 

Development:

 

Publications:

 

  • Mihai Surdeanu and Jordi Turmo, "Semantic Role Labeling Using Complete Syntactic Analysis", CoNLL Shared Task 2005.

 

Scroll to Top