Change search
ReferencesLink to record
Permanent link

Direct link
Mixing and blending syntactic and semantic dependencies
KTH, School of Information and Communication Technology (ICT), Computer and Systems Sciences, DSV.ORCID iD: 0000-0002-4178-2980
Show others and affiliations
2008 (English)In: CoNLL - Proc. Twelfth Conf. Comput. Nat. Lang. Learn., 2008, 248-252 p.Conference paper (Refereed)
Abstract [en]

Our system for the CoNLL 2008 shared task uses a set of individual parsers, a set of stand-alone semantic role labellers, and a joint system for parsing and semantic role labelling, all blended together. The system achieved a macro averaged labelled F 1- score of 79.79 (WSJ 80.92, Brown 70.49) for the overall task. The labelled attachment score for syntactic dependencies was 86.63 (WSJ 87.36, Brown 80.77) and the labelled F 1-score for semantic dependencies was 72.94 (WSJ 74.47, Brown 60.18).

Place, publisher, year, edition, pages
2008. 248-252 p.
, CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning
Keyword [en]
Joint system, Semantic dependency, Semantic roles, Blending, Syntactics, Semantics
National Category
Computer Systems
URN: urn:nbn:se:kth:diva-153336ScopusID: 2-s2.0-84863863788ISBN: 1905593481ISBN: 9781905593484OAI: diva2:755239
12th Conference on Computational Natural Language Learning, CoNLL 2008, 16-17 August 2008, Manchester, United Kingdom

QC 20141014

Available from: 2014-10-14 Created: 2014-10-03 Last updated: 2014-10-14Bibliographically approved

Open Access in DiVA

No full text


Search in DiVA

By author/editor
Velupillai, Sumithra
By organisation
Computer and Systems Sciences, DSV
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 5 hits
ReferencesLink to record
Permanent link

Direct link