This is part of the Alvis search engine framework.

Software

The software presented in this page is related to the linguistic and semantic annotation of documents. The three tools require a standard linux system with libpopt, libxml2, libxslt and libtrish2.

AlvisSemTag

AlvisSemTag attributes an ontology node to each semantic unit in a given document. The attribution is based on class name match and syntactic constraints.

Latest release: 0.4d

Download sources

BioTermTagger

BioTermTagger searches for terms in a document, it searches for candidate phrases or for lemmas in a term dictionary.

Latest release: 0.5d

Download sources

RenBio

RenBio searches for named entities in a document according to a decision tree. The attributes of the tree nodes may be regex matches, dictionary matches or signa words.

Latest release: 0.7d

Download sources

Cadixe

Ressources

D6.3NE

D6.3NE is a framework to prepare a corpus as a training set for named entity recognition. The classifiers produced by this framework may be used by RenBio.

Download D6.3NE
Download gene names corpus

Gene names list

Download Gene list
Download Gene homonyms