To the top

Page Manager: Webmaster
Last update: 9/11/2012 3:13 PM

Tell a friend about this page
Print version

Training a Swedish Consti… - University of Gothenburg, Sweden Till startsida
To content Read more about how we use cookies on

Training a Swedish Constituency Parser on Six Incompatible Treebanks

Conference paper
Authors Richard Johansson
Yvonne Adesam
Published in Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC 2020)
Publisher European Language Resources Association (ELRA)
Publication year 2020
Published at Department of Swedish
Department of Computer Science and Engineering (GU)
Language en
Keywords parsing, Swedish, syntax, neural networks
Subject categories Swedish language, Computational linguistics, Language Technology (Computational Linguistics)


We investigate a transition-based parser that usesEukalyptus, a function-tagged constituent treebank for Swedish which includesdiscontinuous constituents. In addition, we show that the accuracy of this parser can be improved by using a multitask learning architecture that makes it possible to train the parser on additional treebanks that use other annotation models.

Page Manager: Webmaster|Last update: 9/11/2012

The University of Gothenburg uses cookies to provide you with the best possible user experience. By continuing on this website, you approve of our use of cookies.  What are cookies?