MLego reuses and merges materialized LDA models to answer ad-hoc topic queries quickly, using hierarchical plan search and batch reordering to keep the cost low.
The main challenge of such a ”generate- and-rank” method is that there are an exponential number of candidate plans, and the plan generation is time-consuming
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MLego: Interactive and Scalable Topic Exploration Through Model Reuse
MLego reuses and merges materialized LDA models to answer ad-hoc topic queries quickly, using hierarchical plan search and batch reordering to keep the cost low.