SiBert: Enhanced Chinese Pre-trained Language Model with Sentence Insertion.
Jiahao ChenChenjie CaoXiuyan JiangPublished in: LREC (2020)
Keyphrases
- language model
- pre trained
- text summarization
- language modeling
- document level
- query expansion
- training data
- information retrieval
- dependency structure
- n gram
- document retrieval
- probabilistic model
- ad hoc information retrieval
- retrieval model
- mixture model
- speech recognition
- sentence retrieval
- smoothing methods
- control signals
- test collection
- training examples
- data sets
- part of speech
- information extraction
- pseudo relevance feedback
- natural language processing
- context sensitive
- word segmentation
- question answering
- query terms
- statistical machine translation
- relevance model
- linguistic features
- translation model
- document collections
- machine learning