Analyzing the Structure of Attention in a Transformer Language Model.
Jesse VigYonatan BelinkovPublished in: CoRR (2019)
Keyphrases
- language model
- language modeling
- dependency structure
- n gram
- probabilistic model
- speech recognition
- document retrieval
- context sensitive
- language modelling
- information retrieval
- retrieval model
- statistical language models
- test collection
- mixture model
- query expansion
- query terms
- vector space model
- smoothing methods
- ad hoc information retrieval
- machine learning
- pseudo relevance feedback
- em algorithm
- feature selection
- word clouds
- language model for information retrieval