L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models.
Ravindra NayakRaviraj JoshiPublished in: CoRR (2022)
Keyphrases
- language model
- statistical machine translation
- language modeling
- cross lingual
- comparable corpora
- n gram
- cross language retrieval
- machine translation
- language identification
- translation model
- speech recognition
- retrieval model
- context sensitive
- document retrieval
- probabilistic model
- language modelling
- query expansion
- indian languages
- information retrieval
- query terms
- cross language
- multiword
- statistical language models
- test collection
- natural language
- language models for information retrieval
- relevance model
- target language
- pseudo relevance feedback
- vector space model
- smoothing methods
- language independent
- ad hoc information retrieval
- document ranking
- retrieval effectiveness
- named entity recognition
- text classification