Universal Language Model Fine-Tuning with Subword Tokenization for Polish.
Piotr CzaplaJeremy HowardMarcin KardasPublished in: CoRR (2018)
Keyphrases
- fine tuning
- language model
- n gram
- language modeling
- speech recognition
- document retrieval
- out of vocabulary
- probabilistic model
- language independent
- information retrieval
- language modelling
- query expansion
- retrieval model
- smoothing methods
- ad hoc information retrieval
- context sensitive
- query terms
- statistical language models
- pseudo relevance feedback
- relevance model
- named entities
- spoken document retrieval
- document ranking
- fine tuned
- mixture model
- test collection
- document length
- word segmentation
- translation model
- text retrieval
- co occurrence
- statistical machine translation
- text classification
- vector space model
- statistical language modeling
- language models for information retrieval