Dataverse: Open-Source ETL (Extract, Transform, Load) Pipeline for Large Language Models.
Hyunbyung ParkSukyung LeeGyoungjin GimYungi KimDahyun KimChanjun ParkPublished in: CoRR (2024)
Keyphrases
- language model
- open source
- language modeling
- probabilistic model
- n gram
- document retrieval
- information retrieval
- language modelling
- retrieval model
- business intelligence
- speech recognition
- query expansion
- statistical language models
- context sensitive
- test collection
- data warehouse
- query terms
- language models for information retrieval
- ad hoc information retrieval
- pseudo relevance feedback
- case study
- relevance model
- document ranking
- smoothing methods
- data integration
- language modeling approaches
- vector space model
- machine learning
- search engine