User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

Named Entity Recognition for German Using Conditional Random Fields and Linguistic Resources

Primary tabs

Watrin, Patrick [UCL] de Viron, Louis [Earlytracks] Lebailly, Denis [Earlytracks] Constant, Mathieu [Atilf] Weiser, Stéphanie [Earlytracks]

This paper presents a Named Entity Recognition system for German based on Conditional Random Fields. The model also includes language-independant features and features computed form large coverage lexical resources. Along side the results themselves, we show that by adding linguistic resources to a probabilistic model, the results improve significantly.

Document type Communication à un colloque (Conference Paper) – Présentation orale avec comité de sélection
Publication date 2014
Language Anglais
Conference "Konvens", Hildesheim, Germany (du 08/10/2014 au 10/10/2014)
Peer reviewed yes
issn -
e-issn -
Host document "Proceedings of the GermEval 2014 Named Entity Recognition Shared Task (KONVENS 2014)" (ISBN : 978-3-934105-47-8)
Publication status Publié
Affiliation Earlytracks
Keywords Natural language processing ; Named entities recognition ; Conditional random fields ; Linguistic resources
Links
Bibliographic reference Watrin, Patrick ; de Viron, Louis ; Lebailly, Denis ; Constant, Mathieu ; Weiser, Stéphanie. Named Entity Recognition for German Using Conditional Random Fields and Linguistic Resources.Konvens (Hildesheim, Germany, du 08/10/2014 au 10/10/2014). In: Proceedings of the GermEval 2014 Named Entity Recognition Shared Task (KONVENS 2014), 2014
Permanent URL http://hdl.handle.net/2078/213570