Papers by Gengyuan Shi
Adaptive and Robust Translation from Natural Language to Multi-model Query Languages (2025.acl-long)
Copied to clipboard
| Challenge: | Multi-model databases and polystore systems are increasingly studied for managing multi-model data holistically. |
| Approach: | They propose an adaptive Text-to-MMQL framework that includes a schema embedding module and an MMQl representation strategy to generate concise intermediate query formats with error correction in generated queries. |
| Outcome: | The proposed framework achieves over 9% accuracy improvement over baseline methods. |