TU Darmstadt / ULB / TUbiblio

DBPal: Weak Supervision for Learning a Natural Language Interface to Databases

Weir, Nathaniel ; Crotty, Andrew ; Galakatos, Alex ; Ilkhechi, Amir ; Ramaswamy, Shekar ; Bhushan, Rohin ; Cetintemel, Ugur ; Utama, Prasetya ; Geisler, Nadja ; Hättasch, Benjamin ; Eger, Steffen ; Binnig, Carsten (2019)
DBPal: Weak Supervision for Learning a Natural Language Interface to Databases.
1st International Workshop on Conversational Access to Data (CAST) in conj. with the 45th International Conference on Very Large Data Bases (VLDB). Los Angeles, California, USA
Conference or Workshop Item, Bibliographie

Abstract

This paper describes DBPal, a new system to translate natural language utterances into SQL statements using a neural machine translation model. While other recent approaches use neural machine translation to implement a Natural Language Interface to Databases (NLIDB), existing techniques rely on supervised learning with manually curated training data, which results in substantial overhead for supporting each new database schema. In order to avoid this issue, DBPal implements a novel training pipeline based on weak supervision that synthesizes all training data from a given database schema. In our evaluation, we show that DBPal can outperform existing rule-based NLIDBs while achieving comparable performance to other NLIDBs that leverage deep neural network models without relying on manually curated training data for every new database schema.

Item Type: Conference or Workshop Item
Erschienen: 2019
Creators: Weir, Nathaniel ; Crotty, Andrew ; Galakatos, Alex ; Ilkhechi, Amir ; Ramaswamy, Shekar ; Bhushan, Rohin ; Cetintemel, Ugur ; Utama, Prasetya ; Geisler, Nadja ; Hättasch, Benjamin ; Eger, Steffen ; Binnig, Carsten
Type of entry: Bibliographie
Title: DBPal: Weak Supervision for Learning a Natural Language Interface to Databases
Language: English
Date: 30 August 2019
Place of Publication: Los Angeles, California, USA
Event Title: 1st International Workshop on Conversational Access to Data (CAST) in conj. with the 45th International Conference on Very Large Data Bases (VLDB)
Event Location: Los Angeles, California, USA
Abstract:

This paper describes DBPal, a new system to translate natural language utterances into SQL statements using a neural machine translation model. While other recent approaches use neural machine translation to implement a Natural Language Interface to Databases (NLIDB), existing techniques rely on supervised learning with manually curated training data, which results in substantial overhead for supporting each new database schema. In order to avoid this issue, DBPal implements a novel training pipeline based on weak supervision that synthesizes all training data from a given database schema. In our evaluation, we show that DBPal can outperform existing rule-based NLIDBs while achieving comparable performance to other NLIDBs that leverage deep neural network models without relying on manually curated training data for every new database schema.

Uncontrolled Keywords: dm, dm_nlidb, dm_dbpal
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Data Management (2022 umbenannt in Data and AI Systems)
DFG-Graduiertenkollegs
DFG-Graduiertenkollegs > Research Training Group 1994 Adaptive Preparation of Information from Heterogeneous Sources
Date Deposited: 24 Jul 2019 13:17
Last Modified: 21 Apr 2020 15:08
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details