Unlearning Bias in Language Models by Partitioning Gradients.
Charles YuSullam JeoungAnish KasiPengfei YuHeng JiPublished in: ACL (Findings) (2023)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- probabilistic model
- speech recognition
- information retrieval
- language modelling
- retrieval model
- query expansion
- ad hoc information retrieval
- test collection
- smoothing methods
- context sensitive
- statistical language models
- word error rate
- language model for information retrieval
- query terms
- information extraction
- document ranking
- relevance model
- okapi bm
- active learning
- decision trees