From Natural Language Processing to Neural Databases

Summary: Proposes neural databases that use transformer models as localized answer-derivation engines over schema-free natural-language facts, enabling integration with structured and multimodal data. NeuralDB handles select-project-join queries accurately, but exposes major scalability, set-operation, and aggregation challenges. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: 12482
Venue: VLDB
Year: 2021
Pagerank: 9.0215773e-05
Overall Rank: 2,175 | 85.08%
DOI: 10.14778/3447689.3447706

Incoming Non-self Citations Over Time

Authors

1. James Thorne (Meta; University of Cambridge)
2. Majid Yazdani (Meta)
3. Marzieh Saeidi (Meta)
4. Fabrizio Silvestri (Meta)
5. Sebastian Riedel (Meta; University College London)
6. Alon Halevy (Meta)

BibTeX Citation

@article{thorne_vldb21,
        title = {{From Natural Language Processing to Neural Databases}},
        author = {Thorne, James and Yazdani, Majid and Saeidi, Marzieh and Silvestri, Fabrizio and Riedel, Sebastian and Halevy, Alon},
        journal = {PVLDB},
        series = {{VLDB} '21},
        volume = {14},
        number = {6},
        pages = {1033--1039},
        doi = {10.14778/3447689.3447706},
        url = {https://doi.org/10.14778/3447689.3447706},
        year = {2021}
}

Incoming Citations (Sorted by Pagerank)

Showing 10 of 10 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
950	CAESURA: Language Models as Multi-Modal Query Planners	2024	CIDR	0.0001302491
4,045	Logical and Physical Optimizations for SQL Query Execution over Large Language Models	2025	SIGMOD	6.9394654e-05
4,449	From BERT to GPT-3 Codex: Harnessing the Potential of Very Large Language Models for Data Management	2022	VLDB	6.697553e-05
4,687	Knowledge Graphs 2021: A Data Odyssey	2021	VLDB	6.5620198e-05
5,354	Can Large Language Models Predict Data Correlations from Column Names?	2023	VLDB	6.2515841e-05
6,371	QUEST: Query Optimization in Unstructured Document Analysis	2025	VLDB	5.8962187e-05
6,545	DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models	2024	SIGMOD	5.8454882e-05
8,340	Doctopus: Budget-aware Structural Table Extraction from Unstructured Documents	2025	VLDB	5.4487212e-05
9,505	TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations	2025	VLDB	5.258497e-05
11,546	Pythia: Unsupervised Generation of Ambiguous Textual Claims from Relational Data	2022	SIGMOD	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 5 of 5 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
43	The Case for Learned Index Structures	2018	SIGMOD	0.00046060254
141	Deep Entity Matching with Pre-Trained Language Models	2021	VLDB	0.0002964847
176	Deep Learning for Entity Matching: A Design Space Exploration	2018	SIGMOD	0.00027191081
179	Constructing an Interactive Natural Language Interface for Relational Databases	2015	VLDB	0.00026838277
1,540	Crossing the Structure Chasm	2003	CIDR	0.00010430413

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	4,602	Provenance for Natural Language Queries	2017	VLDB
2	3,354	MT-Teql: Evaluating and Augmenting Neural NLIDB on Real-world Linguistic and Schema Variations	2022	VLDB
3	11,748	Toward Pure Natural Language Interaction with Databases	2020	CIDR
4	2,602	NL2SQL is a solved problem... Not!	2024	CIDR
5	3,339	A Deep Dive into Deep Learning Approaches for Text-to-SQL Systems	2021	SIGMOD
6	4,836	Transformers for Tabular Data Representation: A Tutorial on Models and Applications	2022	VLDB
7	865	Natural language to SQL: Where are we today?	2020	VLDB
8	5,078	State of the Art and Open Challenges in Natural Language Interfaces to Data	2020	SIGMOD
9	9,870	Natural Language to SQL: State of the Art and Open Problems	2025	VLDB
10	6,870	Natural Language Interfaces for Databases with Deep Learning	2023	VLDB