Title
Brutus: a semantic role labeling system incorporating CCG, CFG, and dependency features
Abstract
We describe a semantic role labeling system that makes primary use of CCG-based features. Most previously developed systems are CFG-based and make extensive use of a treepath feature, which suffers from data sparsity due to its use of explicit tree configurations. CCG affords ways to augment treepath-based features to overcome these data sparsity issues. By adding features over CCG word-word dependencies and lexicalized verbal subcategorization frames ("supertags"), we can obtain an F-score that is substantially better than a previous CCG-based SRL system and competitive with the current state of the art. A manual error analysis reveals that parser errors account for many of the errors of our system. This analysis also suggests that simultaneous incremental parsing and semantic role labeling may lead to performance gains in both tasks.
Year
Venue
Keywords
2009
ACL/IJCNLP
previous ccg-based srl system,extensive use,primary use,ccg affords way,data sparsity issue,ccg word-word dependency,ccg-based feature,semantic role,dependency feature,current state,manual error analysis,semantic role labeling
Field
DocType
Volume
Subcategorization,Computer science,Speech recognition,Natural language processing,Artificial intelligence,Parsing,Semantic role labeling
Conference
P09-1
Citations 
PageRank 
References 
10
0.58
17
Authors
3
Name
Order
Citations
PageRank
Stephen A. Boxwell1262.32
Dennis Mehay2393.99
Chris Brew332144.44