NLP-LTU at SemEval-2023 Task 10: The Impact of Data Augmentation and Semi-Supervised Learning Techniques on Text Classification Performance on an Imbalanced Dataset.
Sana Sabah Al-AzzawiGyörgy KovácsFilip NilssonTosin P. AdewumiMarcus LiwickiPublished in: CoRR (2023)
Keyphrases
- semi supervised learning
- labeled data
- unlabeled data
- text classification
- data sets
- training data
- raw data
- semi supervised
- labeled and unlabeled data
- data analysis
- co training
- learning models
- supervised learning
- text categorization
- unsupervised learning
- natural language processing
- small number
- active learning
- prior knowledge
- feature selection
- data points
- training samples
- high dimensional
- pairwise
- machine learning