Recherche – Développement – Innovation
Abstract Wikipedia guidelines for authors stress the importance of references since only knowledge already published somewhere else should be inserted in the collaborative encyclopedia. However most bibliographic references are not normalized because various citation...
Le Salon Innovative SHS a pour but de présenter les savoir-faire des unités de recherche en sciences humaines et sociales et valoriser leurs acquis vers le monde économique et social dans les domaines du...
In this post, we will first try to see the impact of training set’s nature on the performance of automatic annotation. Secondly, we will try to see how well our system handles multilingual documents....
In this post we present the influence of part-of-speech and stemming labeling on automatic annotation of bibliographical references. Our reference annotator software Bilbo combines the following global features and local features : Feature Name...
BILBO is an open source software for automatic annotation of bibliographic reference. It provides the segmentation and tagging of input string. It is principally based on Conditional Random Fields (CRFs), machine learning technique to...
Pour cette évaluation, nous nous sommes basés sur le corpus 3 de Bilbo établi à partir de documents extraits de la plateforme Revues.org. Ce troisième corpus a été spécialement conçu afin de mettre en...
Début mars, OpenEdition a déployé sur la plateforme Revues.org son outil d’annotation automatique des références bibliographiques, Bilbo, dans le cadre du programme de recherche et développement « Robust and Language Independent Machine Learning Approaches...
BILBO : Automatic reference labeling (C) Copyright 2013 by Young-Min Kim and Jade Tavernier. written by Young-Min Kim, modified by Jade Tavernier. BILBO is an open source software for automatic annotation of bibliographic reference....
—————————————— BILBO : automatic reference labeling —————————————— Usage: python src/bilbo/Main.py [options] <input data folder> <output data folder> e.g. training: python src/bilbo/Main.py -T -t bibl Data/train/ Result/train/ labeling: python src/bilbo/Main.py -L -t bibl -d Data/test/...
Cette évaluation concerne le deuxième corpus d’apprentissage de Bilbo sur les références bibliographiques situées dans les notes de bas de page et qui conservent un aspect normé comme les références du premier corpus1. Les...
We present three corpora constructed by Elodie Faath. Young-Min Kim and Patrice Bellot will present the corpora detail on May 23 2012 at LREC conference in Istanbul. On this occasion, we distribute our first corpus...
An idea, which naturally stuck us, is to try out learning a model with a complete proper noun feature set for each strategy. It will give us an objective upper bound on the annotation...
We extract seven different learning sets according to the defined strategies in the previous post. Several important fields are selected for the comparison including the surname, forename and place fields that are our main...
In the previous experiments on proper noun lists, certain author names were omitted because of parsing error. We deduce from this inadvertent mistake and the degradation of performance that we would have an improved...
Excluding any errors in manual annotation is hard to be achieved especially when the annotation structure is complex and data size is not small as ours. But the quality of manual annotation is one...
