Simple Text Detoxification by Identifying a Linear Toxic Subspace in Language Model Embeddings.
Andrew WangMohit SudhakarYangfeng JiPublished in: CoRR (2021)
Keyphrases
- language model
- language modeling
- information retrieval
- document retrieval
- n gram
- retrieval model
- hilbert space
- probabilistic model
- speech recognition
- low dimensional
- test collection
- document level
- language modelling
- mixture model
- high dimensional data
- dimensionality reduction
- query expansion
- vector space model
- context sensitive
- text retrieval
- principal component analysis
- smoothing methods
- statistical language models
- ad hoc information retrieval
- query terms
- hidden markov models
- statistical machine translation
- keywords