Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models.
Tyler A. ChangYifan XuWeijian XuZhuowen TuPublished in: CoRR (2021)
Keyphrases
- language model
- relative position
- pre trained
- language modeling
- geometric properties
- n gram
- speech recognition
- probabilistic model
- information retrieval
- training data
- query expansion
- training examples
- spatial relationships
- smoothing methods
- language models for information retrieval
- control signals
- relevance model
- multiscale
- decision trees