A weakly supervised textual entailment approach to zero-shot text classification.
Marc PàmiesJoan LlopFrancesco MultariNicolau Duran-SilvaCésar Parra-RojasAitor Gonzalez-AgirreFrancesco Alessandro MassucciMarta VillegasPublished in: EACL (2023)
Keyphrases
- weakly supervised
- textual entailment
- semantic features
- text classification
- relation extraction
- machine learning
- text categorization
- text mining
- bag of words
- object class
- feature selection
- text documents
- topic models
- labeled data
- wordnet
- semantic information
- natural language processing
- n gram
- knn
- multi label
- low level features
- object categories
- visual features
- object detection
- superpixels
- named entities
- support vector
- semantic similarity
- unlabeled data
- information extraction
- low level
- training data
- clustering algorithm
- learning algorithm
- information retrieval