YoungSheldon at SemEval-2021 Task 5: Fine-tuning Pre-trained Language Models for Toxic Spans Detection using Token classification Objective.
Mayukh SharmaIlanthenral KandasamyW. B. VasanthaPublished in: SemEval@ACL/IJCNLP (2021)
Keyphrases
- language model
- fine tuning
- pre trained
- language modeling
- probabilistic model
- retrieval model
- n gram
- pattern recognition
- query expansion
- document retrieval
- language modelling
- text classification
- test collection
- speech recognition
- neural network
- support vector
- feature vectors
- language models for information retrieval
- statistical language models
- decision trees
- supervised learning
- relevance model
- information retrieval
- image classification
- feature extraction
- query terms
- training examples
- smoothing methods
- training set
- feature space