LANTERN: Boredom-conscious Natural Language Description Generation of Query Execution Plans for Database Education
Summary: LANTERN generates natural-language descriptions of query execution plans to aid database education. It offers POOL, a generic declarative framework for SMEs to author NL descriptions of physical operators, and combines rule-based and deep-learning techniques to diversify explanations and curb learner boredom. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Peng Chen (Xidian University)
- 2. Hui Li (Xidian University)
- 3. Sourav S Bhowmick (Nanyang Technological University)
- 4. Shafiq R Joty (Nanyang Technological University)
- 5. Weiguo Wang (Xidian University)
BibTeX Citation
@inproceedings{chen_sigmod22,
title = {{LANTERN: Boredom-conscious Natural Language Description Generation of Query Execution Plans for Database Education}},
author = {Chen, Peng and Li, Hui and Bhowmick, Sourav S and Joty, Shafiq R and Wang, Weiguo},
series = {{SIGMOD} '22},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3514221.3520165},
url = {https://dl.acm.org/doi/10.1145/3514221.3520165},
year = {2022}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 5,881 | MOCHA: A Tool for Visualizing Impact of Operator Choices in Query Execution Plans for Database Education | 2022 | VLDB | 6.0529753e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 84 | Learned Cardinalities: Estimating Correlated Joins with Deep Learning | 2019 | CIDR | 0.00035838391 |
| 865 | Natural language to SQL: Where are we today? | 2020 | VLDB | 0.00013521464 |
| 9,112 | Towards Enhancing Database Education: Natural Language Generation Meets Query Execution Plans | 2021 | SIGMOD | 5.3218986e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 2,553 | LLM-R^2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency | 2025 | VLDB |
| 2 | 4,602 | Provenance for Natural Language Queries | 2017 | VLDB |
| 3 | 7,718 | Bootstrapping an End-to-End Natural Language Interface for Databases | 2019 | SIGMOD |
| 4 | 9,870 | Natural Language to SQL: State of the Art and Open Problems | 2025 | VLDB |
| 5 | 11,748 | Toward Pure Natural Language Interaction with Databases | 2020 | CIDR |
| 6 | 10,510 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |
| 7 | 2,079 | DBPal: A Fully Pluggable NL2SQL Training Pipeline | 2020 | SIGMOD |
| 8 | 2,778 | DBPal: A Learned NL-Interface for Databases | 2018 | SIGMOD |
| 9 | 11,855 | NEURON: Query Execution Plan Meets Natural Language Processing For Augmenting DB Education | 2019 | SIGMOD |
| 10 | 9,112 | Towards Enhancing Database Education: Natural Language Generation Meets Query Execution Plans | 2021 | SIGMOD |