Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Automatically Selected Skip Edges in Conditional Random Fields for Named Entity Recognition

: Klinger, R.

Volltext (PDF; )

Savova, G.:
Proceedings of the Workshop on Biomedical Natural Language Processing, BiomedNLP 2011 : 15 September, 2011, Hissar, Bulgaria : held in conjunction with the 8th International Conference Recent Advances in Natural Language Processing, RANLP 2011
Shoumen: INCOMA, 2011
ISBN: 978-954-452020-5
Workshop on Biomedical Natural Language Procession (BiomedNLP) <2011, Hissar/Bulgaria>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer SCAI ()

Incorporating distant information via manually selected skip chain templates has been shown to be beneficial for the performance of conditional random field models in contrast to a simple linear chain based structure (Sutton and McCallum, 2007; Galley, 2006; Liu et al., 2010). The set of properties to be captured by a template is typically manually chosen with respect to the application domain.
In this paper, a search strategy to find meaningful skip chains independent from the application domain is proposed. From a huge set of potentially beneficial templates, some can be shown to have a positive impact on the performance. The search for a meaningful graphical structure demonstrates the usefulness of the approach with an increase of nearly 2% F1 measure on a publicly available data set (Klinger et al., 2008).