On the Branching Bias of Syntax Extracted from Pre-trained Language Models.
Huayang LiLemao LiuGuoping HuangShuming ShiPublished in: EMNLP (Findings) (2020)
Keyphrases
- language model
- pre trained
- language modeling
- probabilistic model
- document retrieval
- n gram
- speech recognition
- test collection
- retrieval model
- information retrieval
- language modelling
- statistical language models
- language models for information retrieval
- smoothing methods
- query expansion
- training data
- document ranking
- context sensitive
- control signals
- relevance model
- machine learning
- training examples
- data sets