Publication Search Form




We found publication with these paramters.

Combining labelled and unlabelled data : a case study on Fisher kernels and transductive inference for biological entity recognition

Cyril Goutte, Hervé Dejean, Eric Gaussier, Jean-Michel Renders, Nicola Cancedda
We address the problem of using partially labelled data, eg large collection were only few data is annotated, for extracting entities. Our approach relies on a combination of probabilistic models, which we use to model the generation of entitties and their context, and kernel machines, which implement powerful categorisers based on a similarity measure and some labelled data. This combination takes the form of the so-called Fisher Kernels which implement a similarity based on an underlying probabilistic model. Such kernels are compared with transductive inference, an alternative approach to combining labelled and unlabelled data, again coupled with Support Vector Machines. Experiments are performed on a database of abstracts extracted from Medline.
Proc. of Sixth Conference on Natural Language Learning (CoNLL-2002), Taipei, Taiwan, 24-25 August, 2002.

Attachments (41.82 kB)