Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences.
Genta Indra WinataAndrea MadottoChien-Sheng WuPascale FungPublished in: CoRR (2019)
Keyphrases
- synthetic data
- language model
- language modeling
- language modeling approaches
- probabilistic model
- document level
- n gram
- language modelling
- dependency structure
- document retrieval
- information retrieval
- statistical language models
- speech recognition
- real image data
- real world
- sentence retrieval
- context sensitive
- smoothing methods
- ad hoc information retrieval
- query expansion
- test collection
- data sets
- natural language
- document ranking
- vector space model
- retrieval model
- multiword
- language models for information retrieval
- query terms
- passage retrieval
- okapi bm
- translation model
- document length
- hidden markov models
- relevance model