Automatically Selected Skip Edges in Conditional Random Fields for Named Entity Recognition
Klinger, Roman (2011): Automatically Selected Skip Edges in Conditional Random Fields for Named Entity Recognition, in: Ruslan Mitkov, Galia Angelova, Ruslan Mitkov, u. a. (Hrsg.), Proceedings of the International Conference Recent Advances in Natural Language Processing 2011, Hissar: Association for Computational Linguistics, S. 580–585.
Details
- Fakultät/Lehrstuhl
- Autorin(nen)/Autor(en)
- Titel des Sammelwerks
- Proceedings of the International Conference Recent Advances in Natural Language Processing 2011
- Herausgeberin(nen)/Herausgeber des Sammelwerks
- Mitkov, RuslanAngelova, Galia
- Herausgebende Institution
- Association for Computational Linguistics
- Konferenz
- RANLP, Hissar, Bulgaria
- Verlagsangabe
- Association for Computational Linguistics : Hissar
- Erscheinungsjahr
- 2011
- Sprache(n)
- Englisch
- URL
- Abstract
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 im- pact 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).
- GND-Schlagwort(e)
- Named Entity RecognitionComputerlinguistik
- Freie Schlagwort(e)
- Automatically Selected Skip Edges
- DDC-Klassifikation
- 004 Computer science
- RVK-Klassifikation
- ST 306
- Peer Reviewed
- ja
- Internationale Verbreitung
- ja
- Open-Access-Zeitschrift
- ja
- Dokumenttyp
- Konferenzveröffentlichung
- URI
- Datum der Freischaltung
- 07.03.2024