NEURAL NETWORK BASED TRANSLATION OF NATURAL LANGUAGE QUERIES TO DATABASE QUERIES

Title:

NEURAL NETWORK BASED TRANSLATION OF NATURAL LANGUAGE QUERIES TO DATABASE QUERIES

Document Type and Number:

WIPO Patent Application WO/2018/213530

Kind Code:

A3

Abstract:

A computing system uses neural networks to translate natural language queries to database queries. The computing system uses a plurality of machine learning based models, each machine learning model for generating a portion of the database query. The machine learning models use an input representation generated based on terms of the input natural language query, a set of columns of the database schema, and the vocabulary of a database query language, for example, structured query language SQL. The plurality of machine learning based models may include an aggregation classifier model for determining an aggregation operator in the database query, a result column predictor model for determining the result columns of the database query, and a condition clause predictor model for determining the condition clause of the database query. The condition clause predictor is based on reinforcement learning.

More Like This:

WO/2019/103484	MULTI-MODAL EMOTION RECOGNITION DEVICE, METHOD AND STORAGE MEDIUM USING ARTIFICIAL INTELLIGENCE
JP2000066703	SELF BIAS CONDITIONING DEVICE
JP6799197	Neural network construction device, information processing device, neural network construction method and program

Inventors:

ZHONG VICTOR (US)
XIONG CAIMING (US)
SOCHER RICHARD (US)

Application Number:

PCT/US2018/033099

Publication Date:

January 24, 2019

Filing Date:

May 17, 2018

Export Citation:

Click for automatic bibliography generation Help

Assignee:

SALESFORCE COM INC (US)
ZHONG VICTOR (US)
XIONG CAIMING (US)
SOCHER RICHARD (US)

International Classes:

G06N3/08

Foreign References:

US20110314010A1	2011-12-22
US8156145B2	2012-04-10
US20160171050A1	2016-06-16
US20170109355A1	2017-04-20
US8380645B2	2013-02-19

Other References: