Extraction des caractéristiques lexico-grammaticales et couplage des unités CRF (Conditional Random Field) au réseau de neurones profond pour l'extraction des aspects.
Saint Germes Bienvenu Bengono ObiangNorbert TsopzéPublished in: ARIMA J. (2020)
Keyphrases
- conditional random fields
- information extraction
- crf model
- named entity recognition
- random fields
- maximum entropy
- graphical models
- probabilistic model
- markov random field
- long range
- generative model
- hidden markov models
- pairwise
- semantic segmentation
- contextual features
- efficient inference
- image labeling
- sequence labeling
- higher order
- max margin
- segmentation method
- information retrieval
- superpixels
- fully connected
- active learning
- multiscale
- learning algorithm