Anchoring Fine-tuning of Sentence Transformer with Semantic Label Information for Efficient Truly Few-shot Classification.
Amalie Brogaard PauliLeon DerczynskiIra AssentPublished in: EMNLP (2023)
Keyphrases
- fine tuning
- label information
- semi supervised
- dimensionality reduction
- class labels
- decision trees
- natural language
- training data
- labeled data
- feature extraction
- video sequences
- classification models
- distance metric
- feature vectors
- semantic information
- classification accuracy
- geometric structure
- unlabeled data
- machine learning
- text classification
- neural network
- unsupervised learning
- pattern recognition
- image classification
- domain specific
- principal component analysis
- training samples
- machine learning algorithms
- supervised learning
- feature space
- support vector
- computer vision
- learning algorithm
- data sets