TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
SQL Parsing	Academic	Iyer et al.	Question Split	76	# 2
SQL Parsing	Academic	Iyer et al.	Query Split	70	# 2
SQL Parsing	Advising	Iyer et al.	Question Split	41	# 3
SQL Parsing	Advising	Iyer et al.	Query Split	1	# 1
SQL Parsing	ATIS	Iyer et al.	Question Split	45	# 2
SQL Parsing	ATIS	Iyer et al.	Query Split	17	# 2
SQL Parsing	GeoQuery	Iyer et al.	Question Split	66	# 2
SQL Parsing	GeoQuery	Iyer et al.	Query Split	40	# 1
SQL Parsing	IMDb	Iyer et al.	Question Split	10	# 2
SQL Parsing	IMDb	Iyer et al.	Query Split	4	# 2
SQL Parsing	Restaurants	Iyer et al.,	Question Split	100	# 1
SQL Parsing	Restaurants	Iyer et al.,	Query Split	8	# 1
SQL Parsing	Scholar	Iyer et al.	Question Split	44	# 3
SQL Parsing	Scholar	Iyer et al.	Query Split	3	# 2
SQL Parsing	Yelp	Iyer et al.	Question Split	6	# 2
SQL Parsing	Yelp	Iyer et al.	Query Split	6	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-a-neural-semantic-parser-from-user/sql-parsing-on-restaurants)](https://paperswithcode.com/sota/sql-parsing-on-restaurants?p=learning-a-neural-semantic-parser-from-user)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-a-neural-semantic-parser-from-user/sql-parsing-on-academic)](https://paperswithcode.com/sota/sql-parsing-on-academic?p=learning-a-neural-semantic-parser-from-user)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-a-neural-semantic-parser-from-user/sql-parsing-on-atis)](https://paperswithcode.com/sota/sql-parsing-on-atis?p=learning-a-neural-semantic-parser-from-user)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-a-neural-semantic-parser-from-user/sql-parsing-on-geoquery)](https://paperswithcode.com/sota/sql-parsing-on-geoquery?p=learning-a-neural-semantic-parser-from-user)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-a-neural-semantic-parser-from-user/sql-parsing-on-imdb)](https://paperswithcode.com/sota/sql-parsing-on-imdb?p=learning-a-neural-semantic-parser-from-user)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-a-neural-semantic-parser-from-user/sql-parsing-on-yelp)](https://paperswithcode.com/sota/sql-parsing-on-yelp?p=learning-a-neural-semantic-parser-from-user)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-a-neural-semantic-parser-from-user/sql-parsing-on-advising)](https://paperswithcode.com/sota/sql-parsing-on-advising?p=learning-a-neural-semantic-parser-from-user)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-a-neural-semantic-parser-from-user/sql-parsing-on-scholar)](https://paperswithcode.com/sota/sql-parsing-on-scholar?p=learning-a-neural-semantic-parser-from-user)`

Learning a Neural Semantic Parser from User Feedback

ACL 2017 · Srinivasan Iyer, Ioannis Konstas, Alvin Cheung, Jayant Krishnamurthy, Luke Zettlemoyer ·

We present an approach to rapidly and easily build natural language interfaces to databases for new domains, whose performance improves over time based on user feedback, and requires minimal intervention. To achieve this, we adapt neural sequence models to map utterances directly to SQL with its full expressivity, bypassing any intermediate meaning representations. These models are immediately deployed online to solicit feedback from real users to flag incorrect queries. Finally, the popularity of SQL facilitates gathering annotations for incorrect predictions using the crowd, which is directly used to improve our models. This complete feedback loop, without intermediate representations or database specific engineering, opens up new ways of building high quality semantic parsers. Experiments suggest that this approach can be deployed quickly for any new target domain, as we show by learning a semantic parser for an online academic database from scratch.

PDF Abstract ACL 2017 PDF ACL 2017 Abstract

Code

Add Remove Mark official

No code implementations yet. Submit your code now

Tasks

Add Remove

SQL Parsing

Datasets

IMDb Movie Reviews

ATIS Yelp

Results from the Paper

Edit

Ranked #1 on SQL Parsing on Restaurants

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
SQL Parsing	Academic	Iyer et al.	Question Split	76	# 2	Compare
SQL Parsing	Academic	Iyer et al.	Query Split	70	# 2	Compare
SQL Parsing	Advising	Iyer et al.	Question Split	41	# 3	Compare
SQL Parsing	Advising	Iyer et al.	Query Split	1	# 1	Compare
SQL Parsing	ATIS	Iyer et al.	Question Split	45	# 2	Compare
SQL Parsing	ATIS	Iyer et al.	Query Split	17	# 2	Compare
SQL Parsing	GeoQuery	Iyer et al.	Question Split	66	# 2	Compare
SQL Parsing	GeoQuery	Iyer et al.	Query Split	40	# 1	Compare
SQL Parsing	IMDb	Iyer et al.	Question Split	10	# 2	Compare
SQL Parsing	IMDb	Iyer et al.	Query Split	4	# 2	Compare
SQL Parsing	Restaurants	Iyer et al.,	Question Split	100	# 1	Compare
SQL Parsing	Restaurants	Iyer et al.,	Query Split	8	# 1	Compare
SQL Parsing	Scholar	Iyer et al.	Question Split	44	# 3	Compare
SQL Parsing	Scholar	Iyer et al.	Query Split	3	# 2	Compare
SQL Parsing	Yelp	Iyer et al.	Question Split	6	# 2	Compare
SQL Parsing	Yelp	Iyer et al.	Query Split	6	# 1	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

Learning a Neural Semantic Parser from User Feedback

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove