Revisiting subword tokenization: A case study on affixal negation in large language models.
Thinh TruongYulia OtmakhovaKarin VerspoorTrevor CohnTimothy BaldwinPublished in: NAACL-HLT (2024)
Keyphrases
- language model
- n gram
- language modeling
- speech recognition
- out of vocabulary
- language modelling
- query expansion
- document retrieval
- probabilistic model
- retrieval model
- information retrieval
- test collection
- context sensitive
- language independent
- ad hoc information retrieval
- query terms
- pseudo relevance feedback
- statistical language models
- smoothing methods
- vector space model
- language models for information retrieval
- bayesian networks
- query specific
- document ranking
- query processing
- translation model
- relevance model
- vector space
- text documents
- document length
- named entities
- okapi bm
- hidden markov models
- language model for information retrieval