Using Large Corpus N-gram Statistics to Improve Recurrent Neural Language Models.
Yiben YangJi-Ping WangDoug DowneyPublished in: NAACL-HLT (1) (2019)
Keyphrases
- language model
- n gram
- language modeling
- language modelling
- document retrieval
- probabilistic model
- speech recognition
- language independent
- information retrieval
- test collection
- bag of words
- document level
- query expansion
- statistical language modeling
- multiword
- text classification
- retrieval model
- context sensitive
- query terms
- document ranking
- data mining
- vector space model
- part of speech
- pseudo relevance feedback
- word segmentation
- translation model
- word level
- out of vocabulary
- smoothing methods