Biomedical Event Extraction by Multi-class Classification of Pairs of Text Entities - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

Biomedical Event Extraction by Multi-class Classification of Pairs of Text Entities

Abstract

This paper describes the HDS4NLP en- try to the BioNLP 2013 shared task on biomedical event extraction. This system is based on a pairwise model that transforms trigger classification in a simple multi-class problem in place of the usual multi-label problem. This model facilitates inference compared to global models while relying on richer information compared to usual pipeline approaches. The HDS4NLP system ranked 6th on the Genia task (43.03% f-score), and after fixing a bug discovered after the final submission, it outperforms the winner of this task (with a f-score of 51.15%).
Fichier principal
Vignette du fichier
liu2013bionlp.pdf (133.88 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-00880444 , version 1 (06-11-2013)

Identifiers

  • HAL Id : hal-00880444 , version 1

Cite

Xiao Liu, Antoine Bordes, Yves Grandvalet. Biomedical Event Extraction by Multi-class Classification of Pairs of Text Entities. BioNLP Shared Task 2013 Workshop, Aug 2013, Sofia, Bulgaria. pp.45-49. ⟨hal-00880444⟩
136 View
152 Download

Share

Gmail Facebook Twitter LinkedIn More