Symphony: Towards Natural Language Query Answering over Multi-modal Data Lakes
Summary: Symphony enables NL queries over multi-modal data lakes (tables + text) without upfront integration, using cross-modality representation learning to locate relevant sources. It decomposes NL questions into per-source subqueries, executes them and fuses results; preliminarily validated on Wikipedia tables/text. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Zui Chen (Tsinghua University)
- 2. Zihui Gu (Renmin University of China)
- 3. Lei Cao (Massachusetts Institute of Technology; University of Arizona)
- 4. Ju Fan (Renmin University of China)
- 5. Sam Madden (Massachusetts Institute of Technology)
- 6. Nan Tang (Hamad Bin Khalifa University; Qatar Computing Research Institute)
BibTeX Citation
@inproceedings{chen_cidr23,
address = {Amsterdam, Netherlands},
series = {{CIDR} '23},
title = {{Symphony: Towards Natural Language Query Answering over Multi-modal Data Lakes}},
booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
author = {Chen, Zui and Gu, Zihui and Cao, Lei and Fan, Ju and Madden, Sam and Tang, Nan},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 19 of 19 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 134 | Deep Entity Matching with Pre-Trained Language Models | 2021 | VLDB | 0.00030043481 |
| 329 | Can Foundation Models Wrangle Your Data? | 2023 | VLDB | 0.00020858443 |
| 459 | Delta Lake: High-Performance ACID Table Storage over Cloud Object Stores | 2020 | VLDB | 0.00017856221 |
| 776 | Natural language to SQL: Where are we today? | 2020 | VLDB | 0.00014063545 |
| 972 | The Data Civilizer System | 2017 | CIDR | 0.00012763234 |
| 1,991 | RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation | 2021 | VLDB | 9.2383849e-05 |
| 7,291 | Data Civilizer 2.0: A Holistic Framework for Data Preparation and Analytics | 2019 | VLDB | 5.5642829e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 7,950 | A Natural Language Interface for Querying General and Individual Knowledge | 2015 | VLDB |
| 2 | 4,142 | AOP: Automated and Interactive LLM Pipeline Orchestration for Answering Complex Queries | 2025 | CIDR |
| 3 | 5,862 | SpeakQL: Towards Speech-driven Multimodal Querying of Structured Data | 2020 | SIGMOD |
| 4 | 12,051 | Toward Pure Natural Language Interaction with Databases | 2020 | CIDR |
| 5 | 4,694 | Demonstration of SpeakQL: Speech-driven Multimodal Querying of Structured Data | 2019 | SIGMOD |
| 6 | 180 | Constructing an Interactive Natural Language Interface for Relational Databases | 2015 | VLDB |
| 7 | 10,837 | EcoTable: Cost-effective Table Integration in Data Lakes for Natural Language Queries | 2026 | VLDB |
| 8 | 7,318 | An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models | 2024 | VLDB |
| 9 | 1,846 | From Natural Language Processing to Neural Databases | 2021 | VLDB |
| 10 | 11,852 | VoiceQuerySystem: A Voice-driven Database Querying System Using Natural Language Questions | 2022 | SIGMOD |