DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networks
Summary: DBTagger reframes NLIDB keyword mapping as a sequence tagging problem, using Bi-Directional RNNs with POS features in a multi-task learning setup. End-to-end, schema-independent NLQ-to-SQL tagging attains 92.4% average accuracy across eight datasets and scales to large schemas with speedups. (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. Arif Usta (Bilkent University)
- 2. Akifhan Karakayali (Bilkent University)
- 3. Özgür Ulusoy (Bilkent University)
BibTeX Citation
@article{usta_vldb21,
title = {{DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networks}},
author = {Usta, Arif and Karakayali, Akifhan and Ulusoy, Özgür},
journal = {PVLDB},
series = {{VLDB} '21},
volume = {14},
number = {5},
pages = {813--821},
doi = {10.14778/3446095.3446103},
url = {https://doi.org/10.14778/3446095.3446103},
year = {2021}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 8 of 8 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 178 | Constructing an Interactive Natural Language Interface for Relational Databases | 2015 | VLDB | 0.00026568976 |
| 430 | ATHENA: An Ontology-Driven System for Natural Language Querying over Relational Data Stores | 2016 | VLDB | 0.00018415668 |
| 755 | Natural language to SQL: Where are we today? | 2020 | VLDB | 0.00014210408 |
| 1,217 | SODA: Generating SQL for Business Users | 2012 | VLDB | 0.00011464151 |
| 1,999 | DBPal: A Fully Pluggable NL2SQL Training Pipeline | 2020 | SIGMOD | 9.2108564e-05 |
| 2,747 | DBPal: A Learned NL-Interface for Databases | 2018 | SIGMOD | 8.0453676e-05 |
| 5,143 | State of the Art and Open Challenges in Natural Language Interfaces to Data | 2020 | SIGMOD | 6.2414745e-05 |
| 5,251 | Natural Language Data Management and Interfaces: Recent Development and Open Challenges | 2017 | SIGMOD | 6.1977414e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 2,747 | DBPal: A Learned NL-Interface for Databases | 2018 | SIGMOD |
| 2 | 1,348 | Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks | 2020 | SIGMOD |
| 3 | 3,246 | A Deep Dive into Deep Learning Approaches for Text-to-SQL Systems | 2021 | SIGMOD |
| 4 | 1,209 | CatSQL: Towards Real World Natural Language to SQL Applications | 2023 | VLDB |
| 5 | 2,591 | Text2SQL is Not Enough: Unifying AI and Databases with TAG | 2025 | CIDR |
| 6 | 3,322 | MT-Teql: Evaluating and Augmenting Neural NLIDB on Real-world Linguistic and Schema Variations | 2022 | VLDB |
| 7 | 6,328 | Natural Language Interfaces for Databases with Deep Learning | 2023 | VLDB |
| 8 | 755 | Natural language to SQL: Where are we today? | 2020 | VLDB |
| 9 | 1,815 | From Natural Language Processing to Neural Databases | 2021 | VLDB |
| 10 | 1,999 | DBPal: A Fully Pluggable NL2SQL Training Pipeline | 2020 | SIGMOD |