Beyond Interestingness: Semantic and Context-Aware Natural Language Query Recommendations for Visual Data Analysis
3.40T1 sourcearXiv cs.HC
Source record
Published by arXiv cs.HC (T1 source). The original is at https://arxiv.org/abs/2201.04868.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryA paper presenting QRec-NLI, a natural language interface that augments relational database exploration with semantic- and context-aware next-step query recommendations. It jointly integrates semantic relevance, data interestingness, and context coherence, outperforming interestingness-only and LLM-based baselines in agentic comparisons and a 12-participant user study.
Why it mattersConcrete system for scaffolding multi-step NL data analysis, with measured user study results. Relevant for building or evaluating agentic exploration tools over relational data.
Cited by
No citations on record.