Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes.
Simran AroraBrandon YangSabri EyubogluAvanika NarayanAndrew HojelImmanuel TrummerChristopher RéPublished in: CoRR (2023)
Keyphrases
- language model
- heterogeneous data
- language modeling
- n gram
- probabilistic model
- retrieval model
- speech recognition
- test collection
- database
- document retrieval
- data integration
- information retrieval
- decision trees
- knn
- retrieval systems
- document ranking
- relevance assessments
- language modelling
- statistical language models
- complex data
- co occurrence
- data sources
- metadata
- data mining
- databases