Toxic Speech Detection in Portuguese: A Comparative Study of Large Language Models.
Amanda da Silva OliveiraThiago de Carvalho CecoteJoão Paulo Reis AlvarengaVander Luis de Souza FreitasEduardo José da Silva LuzPublished in: PROPOR (2024)
Keyphrases
- language model
- speech recognition
- language modeling
- word error rate
- n gram
- spoken term detection
- document retrieval
- information retrieval
- language modelling
- retrieval model
- automatic speech recognition
- test collection
- context sensitive
- query expansion
- probabilistic model
- pseudo relevance feedback
- query terms
- language models for information retrieval
- smoothing methods
- speech signal
- statistical language models
- relevance model
- out of vocabulary
- ad hoc information retrieval
- mixture model
- document ranking
- language model for information retrieval
- document length
- term dependencies
- hidden markov models
- clustering algorithm