GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism.
Shuzhou YuanMichael FärberPublished in: CoRR (2024)
Keyphrases
- structural information
- language model
- language modeling
- topological information
- attention mechanism
- n gram
- probabilistic model
- document retrieval
- retrieval model
- language modelling
- statistical language models
- information retrieval
- test collection
- query expansion
- semantic information
- relevance model
- document ranking
- higher level
- language models for information retrieval
- visual attention
- contextual information
- smoothing methods