SATLab at SemEval-2022 Task 4: Trying to Detect Patronizing and Condescending Language with only Character and Word N-grams.
Yves BestgenPublished in: SemEval@NAACL (2022)
Keyphrases
- n gram
- language specific
- character n grams
- language model
- language independent
- variable length
- text classification
- bag of words
- viterbi algorithm
- word segmentation
- optical character recognition
- part of speech
- natural language
- web documents
- language modeling
- character recognition
- word sense disambiguation
- information extraction
- word level
- knowledge discovery
- keywords