Table 4 Evaluation results with a customization performed by the implementers
From: Comparative study on the customization of natural language interfaces to databases
NLIDB | Total queries | Correct w/initial customization | Correct w/fine-tuning | Minutes for customizing one query | Recall w/initial customization (%) | Recall w/fine-tuning (%) |
|---|---|---|---|---|---|---|
ELF | 70 | 7 | 11 | 40 | 10 | 15.7 |
Our NLIDB | 70 | 17 | 63 | 2.6 | 24.28 | 90 |