Incorporating Syntactic Knowledge into Pre-trained Language Model using Optimization for Overcoming Catastrophic Forgetting.
Ran IwamotoIssei YoshidaHiroshi KanayamaTakuya OhkoMasayasu MuraokaPublished in: EMNLP (Findings) (2023)
Keyphrases
- language model
- language modeling
- n gram
- pre trained
- probabilistic model
- smoothing methods
- document retrieval
- information retrieval
- query expansion
- context sensitive
- retrieval model
- ad hoc information retrieval
- speech recognition
- mixture model
- test collection
- query terms
- maximum likelihood
- text classification
- neural network
- training examples
- dependency structure