Change search
ReferencesLink to record
Permanent link

Direct link
Evaluation of local features for argument identification and classification for semantic role labeling
Number of Authors: 3
2008 (English)Conference paper (Refereed)
Abstract [en]

In this paper we present some findings from an evaluation of dependency-based features for argument identification and classification in a pipelined semantic role labeling system. In total over 100 feature types were evaluated. Results indicate that most features can be discarded with sustained or even improved performance. We further find that arguments of nominal and verbal predicates seem to rely on different feature types - while arguments of verbal predicates rely more on structural features, arguments of nominal predicates rely more on lexical features.

Place, publisher, year, edition, pages
2008, 1. , 2 p.
Keyword [en]
Semantic role labeling, Feature evaluation, Dependency-based feature representations
National Category
Computer and Information Science
Identifiers
URN: urn:nbn:se:ri:diva-22923OAI: oai:DiVA.org:ri-22923DiVA: diva2:1042488
Conference
The Second Swedish Language Technology Conference (SLTC-08)
Available from: 2016-10-31 Created: 2016-10-31

Open Access in DiVA

fulltext(70 kB)1 downloads
File information
File name FULLTEXT01.pdfFile size 70 kBChecksum SHA-512
9b2e1ab31a2a2aec4475e2fe0039efd39f4c6cbac6508c066aec38224a8eb199491cf025c81fe6e5fbd2dc513454cd46a2214284282c9d08519e15387bbf836e
Type fulltextMimetype application/pdf

Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 1 downloads
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: 4 hits
ReferencesLink to record
Permanent link

Direct link