UMUTeam at HOMO-MEX 2023: Fine-tuning Large Language Models integration for solving hate-speech detection in Mexican Spanish.
José Antonio García-DíazSalud María Jiménez ZafraRafael Valencia-GarcíaPublished in: IberLEF@SEPLN (2023)
Keyphrases
- language model
- fine tuning
- speech recognition
- language modeling
- word error rate
- n gram
- probabilistic model
- query expansion
- spoken term detection
- document retrieval
- viable alternative
- statistical language models
- test collection
- retrieval model
- language modelling
- automatic speech recognition
- context sensitive
- vector space model
- information retrieval
- language model for information retrieval
- out of vocabulary
- speech signal
- ad hoc information retrieval
- relevance model
- fine tuned
- hidden markov models
- document ranking
- pseudo relevance feedback
- query terms
- data fusion
- search engine
- translation model
- term dependencies
- cross lingual
- smoothing methods
- web search
- text mining
- language models for information retrieval