File(s) not publicly available
Evaluating the accuracy of an unlexicalized statistical parser on the PARC DepBank
presentation
posted on 2023-06-08, 05:27 authored by Ted Briscoe, John CarrollWe evaluate the accuracy of an unlexicalized statistical parser, trained on 4K treebanked sentences from balanced data and tested on the PARC DepBank. We demonstrate that a parser which is competitive in accuracy (without sacrificing processing speed) can be quickly tuned without reliance on large in-domain manually-constructed treebanks. This makes it more practical to use statistical parsers in applications that need access to aspects of predicate-argument structure. The comparison of systems using DepBank is not straightforward, so we extend and validate DepBank and highlight a number of representation and scoring issues for relational evaluation schemes.
History
Publication status
- Published
Page range
41-48Pages
8.0Presentation Type
- paper
Event name
COLING/ACL 2006 Main Conference Poster SessionsEvent location
Sydney, AustraliaEvent type
conferenceDepartment affiliated with
- Informatics Publications
Notes
Association for Computational LinguisticsFull text available
- No
Peer reviewed?
- Yes
Legacy Posted Date
2012-02-06Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC