DBScholar

Back to papers

Synthesizing Natural Language to Visualization (NL2VIS) Benchmarks from NL2SQL Benchmarks

Summary: nvBench is the first nl2vis benchmark, synthesized from nl2sql (Spider) via an AST bridge unifying SQL and vis trees for multiple viz languages. It reduces benchmark creation to 5.7% of manual effort and a seq2vis model trained on nvBench outperforms prior nl2vis methods, with extensive validation. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
6214
Venue
SIGMOD
Year
2021
Pagerank
6.4984309e-05
Overall Rank
4,809 | 67.01%
DOI
10.1145/3448016.3457261

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@inproceedings{luo_sigmod21,
        title = {{Synthesizing Natural Language to Visualization (NL2VIS) Benchmarks from NL2SQL Benchmarks}},
        author = {Luo, Yuyu and Chai, Chengliang and Tang, Nan and Li, Wenbo and Li, Guoliang and Qin, Xuedi},
        series = {{SIGMOD} '21},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3448016.3457261},
        url = {https://dl.acm.org/doi/10.1145/3448016.3457261},
        year = {2021}
}

Incoming Citations (Sorted by Pagerank)

Showing 14 of 14 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 13 of 13 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers