UoB at SemEval-2021 Task 5: Extending Pre-Trained Language Models to Include Task and Domain-Specific Information for Toxic Span Prediction.
Erik YanHarish Tayyar MadabushiPublished in: SemEval@ACL/IJCNLP (2021)
Keyphrases
- language model
- pre trained
- domain specific information
- language modeling
- probabilistic model
- document retrieval
- n gram
- speech recognition
- information retrieval
- query expansion
- training data
- retrieval model
- test collection
- demographic information
- domain ontology
- smoothing methods
- query terms
- control signals
- semi automatic
- co occurrence
- natural language processing
- keyphrases
- domain knowledge
- data analysis