Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training.
Hai YeQingyu TanRuidan HeJuntao LiHwee Tou NgLidong BingPublished in: EMNLP (1) (2020)
Keyphrases
- language model
- pre trained
- language modeling
- n gram
- statistical language models
- probabilistic model
- smoothing methods
- query expansion
- retrieval model
- cross lingual
- document retrieval
- language independent
- test collection
- language modelling
- speech recognition
- information retrieval
- semi supervised learning
- language models for information retrieval
- image features
- document ranking
- high dimensional
- pairwise
- illumination variations
- feature space
- training data
- feature selection
- neural network