From Characters to Words: Hierarchical Pre-trained Language Model for Open-vocabulary Language Understanding.
Li SunFlorian LuisierKayhan BatmanghelichDinei A. F. FlorêncioCha ZhangPublished in: CoRR (2023)
Keyphrases
- language model
- language understanding
- out of vocabulary
- pre trained
- n gram
- language modeling
- natural language understanding
- probabilistic model
- translation model
- speech recognition
- information retrieval
- training examples
- training data
- semantic interpretation
- multiword
- statistical language modeling
- language processing
- query expansion
- retrieval model
- query terms
- test collection
- natural language
- spoken dialogue systems
- dialogue system
- general knowledge
- keywords
- control signals
- search engine
- word segmentation
- part of speech
- word sense disambiguation
- text classification
- decision trees