Méthodologie pour identifier les terrains d'étude dans des corpus scientifiques.
Eric KergosienMarie-Noëlle BessagnetMaguelonne TeisseireJoachim SchöpfelAmin FarvardinStéphane ChaudironBernard JacqueminAnnig Le Parc-LacayrelleMathieu RocheChristian SallaberryJean-Philippe TonneauPublished in: Document Numérique (2017)
Keyphrases
- virtual environment
- test set
- manually annotated
- spoken dialog
- open domain
- newspaper articles
- genetic algorithm
- annotated corpus
- spanish language
- data sets
- word frequencies
- english words
- supervised machine learning
- statistical machine translation
- text corpora
- natural language text
- named entities
- data structure
- learning algorithm
- machine learning