Hybrid Information Retrieval with Masked and Permuted Language Modeling (MPNet) and BM25L for Indonesian Drug Data Retrieval.
Maryamah MaryamahGeraldus WilsenChristeigen Theodore SuhalimRafik SeptianaAziz FajarMahmud Iwan SolihinPublished in: KST (2024)
Keyphrases
- data retrieval
- language modeling
- information retrieval
- retrieval model
- language model
- term weighting
- term weighting schemes
- document retrieval
- information retrieval systems
- retrieval effectiveness
- test collection
- document length
- query expansion
- relevant documents
- search engine
- tf idf
- information extraction
- ir models
- retrieval systems
- databases
- text retrieval
- question answering
- document collections
- relevance model
- query processing
- term frequency
- trec collections
- text mining
- vector space model
- machine translation
- data access
- query terms
- vector space
- web search
- dirichlet prior
- statistical language modeling