Skip to Main content Skip to Navigation
Conference papers

Coopération de méthodes statistiques et symboliques pour l'adaptation non-supervisée d'un système d'étiquetage en entités nommées

Abstract : Named entity recognition and typing is achieved both by symbolic and probabilistic systems. We report on an experiment for making the rule-based system NP, a high-precision system developed on AFP news corpora and relies on the Aleda named entity database, interact with LIANE, a high-recall probabilistic system trained on oral transcriptions from the ESTER corpus. We show that a probabilistic system such as LIANE can be adapted to a new type of corpus in a non-supervized way thanks to large-scale corpora automatically annotated by NP. This adaptation does not require any additional manual anotation and illustrates the complementarity between numeric and symbolic techniques for tackling linguistic tasks.
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/inria-00617068
Contributor : Benoît Sagot <>
Submitted on : Thursday, August 25, 2011 - 10:40:32 PM
Last modification on : Saturday, March 28, 2020 - 2:17:23 AM
Document(s) archivé(s) le : Sunday, December 4, 2016 - 6:21:52 PM

File

taln11entnom.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00617068, version 1

Collections

Citation

Frédéric Béchet, Benoît Sagot, Rosa Stern. Coopération de méthodes statistiques et symboliques pour l'adaptation non-supervisée d'un système d'étiquetage en entités nommées. TALN'2011 - Traitement Automatique des Langues Naturelles, Jun 2011, Montpellier, France. ⟨inria-00617068⟩

Share

Metrics

Record views

673

Files downloads

952