On the Comparability of Pre-trained Language Models.
Matthias AßenmacherChristian HeumannPublished in: SwissText/KONVENS (2020)
Keyphrases
- language model
- pre trained
- language modeling
- training data
- document retrieval
- n gram
- speech recognition
- probabilistic model
- information retrieval
- training examples
- test collection
- retrieval model
- relevance model
- language modelling
- control signals
- query expansion
- statistical language models
- smoothing methods
- language models for information retrieval
- machine learning
- labeled data
- graph cuts
- semi supervised
- training set
- support vector
- clustering algorithm
- neural network
- data sets