ViSoBERT: A Pre-Trained Language Model for Vietnamese Social Media Text Processing.
Nam NguyenThang PhanDuc-Vu NguyenKiet Van NguyenPublished in: EMNLP (2023)
Keyphrases
- text processing
- language model
- pre trained
- social media
- language modeling
- information retrieval
- training data
- document retrieval
- natural language processing
- text mining
- n gram
- training examples
- information extraction
- machine learning
- probabilistic model
- test collection
- mixture model
- speech recognition
- retrieval model
- query expansion
- control signals
- smoothing methods
- query terms
- neural network
- ad hoc information retrieval
- training samples
- cross lingual
- decision trees
- translation model