# 08/03/2020 updated: corrected column name and column name original mismatch in 2 dbs (scholar and formula_1) in tables.json. Also, used process_sql.py to reparse SQL queries (this only affects some models (e.g. RATSQL) which use our parsed SQL as the SQL input).
# 06/01/2020 updated: corrected ~40 annotation errors/mismatches in dev.json
This folder contains the Spider training and dev data sets for the EMNLP 2018 paper Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task.
It contains the following files:
- train_spider.json
# Training Examples: 7000
# Databases: 140
- train_others.json
# Training Examples: 1659
# Databases: 6
- dev.json
# Training Examples: 1034
# Databases: 20
- tables.json
# Databases: 166
- dev_gold.sql
- train_gold.sql
- database/
- README.txt
The official final Spider training data set combines train_spider.json and train_others.json.
The databases used in train_others.json are from Restaurants, GeoQuery, Scholar, Academic, IMDB, and Yelp which are prepared by Finegan-Dollak et al., 2018.
The databases and SQL examples in train_spider.json are originally prepared by us.
For the format of each json file, please refer to our github page https://github.com/taoyds/spider.
In database/, there is one folder for each database which contains the [db_name].sqlite file.
For most databases, we also provide a schema.sql file with SQL statements to create the database.
If you use the dataset, please cite the following papers including Finegan-Dollak et al., 2018 and the original datasets for Restaurants, GeoQuery, Scholar, Academic, IMDB, and Yelp.
@inproceedings{Yu&al.18c,
year = 2018,
title = {Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task},
booktitle = {EMNLP},
author = {Tao Yu and Rui Zhang and Kai Yang and Michihiro Yasunaga and Dongxu Wang and Zifan Li and James Ma and Irene Li and Qingning Yao and Shanelle Roman and Zilin Zhang and Dragomir Radev }
}
@InProceedings{P18-1033,
author = "Finegan-Dollak, Catherine
and Kummerfeld, Jonathan K.
and Zhang, Li
and Ramanathan, Karthik
and Sadasivam, Sesh
and Zhang, Rui
and Radev, Dragomir",
title = "Improving Text-to-SQL Evaluation Methodology",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
year = "2018",
publisher = "Association for Computational Linguistics",
pages = "351--360",
location = "Melbourne, Australia",
url = "http://aclweb.org/anthology/P18-1033"
}
@InProceedings{data-sql-imdb-yelp,
dataset = {IMDB and Yelp},
author = {Navid Yaghmazadeh, Yuepeng Wang, Isil Dillig, and Thomas Dillig},
title = {SQLizer: Query Synthesis from Natural Language},
booktitle = {International Conference on Object-Oriented Programming, Systems, Languages, and Applications, ACM},
month = {October},
year = {2017},
pages = {63:1--63:26},
url = {http://doi.org/10.1145/3133887},
}
@article{data-academic,
dataset = {Academic},
author = {Fei Li and H. V. Jagadish},
title = {Constructing an Interactive Natural Language Interface for Relational Databases},
journal = {Proceedings of the VLDB Endowment},
volume = {8},
number = {1},
month = {September},
year = {2014},
pages = {73--84},
url = {http://dx.doi.org/10.14778/2735461.2735468},
}
@InProceedings{data-atis-geography-scholar,
dataset = {Scholar, and Updated ATIS and Geography},
author = {Srinivasan Iyer, Ioannis Konstas, Alvin Cheung, Jayant Krishnamurthy, and Luke Zettlemoyer},
title = {Learning a Neural Semantic Parser from User Feedback},
booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
year = {2017},
pages = {963--973},
location = {Vancouver, Canada},
url = {http://www.aclweb.org/anthology/P17-1089},
}
@inproceedings{data-geography-original
dataset = {Geography, original},
author = {John M. Zelle and Raymond J. Mooney},
title = {Learning to Parse Database Queries Using Inductive Logic Programming},
booktitle = {Proceedings of the Thirteenth National Conference on Artificial Intelligence - Volume 2},
year = {1996},
pages = {1050--1055},
location = {Portland, Oregon},
url = {http://dl.acm.org/citation.cfm?id=1864519.1864543},
}
@inproceedings{data-restaurants-logic,
author = {Lappoon R. Tang and Raymond J. Mooney},
title = {Automated Construction of Database Interfaces: Intergrating Statistical and Relational Learning for Semantic Parsing},
booktitle = {2000 Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora},
year = {2000},
pages = {133--141},
location = {Hong Kong, China},
url = {http://www.aclweb.org/anthology/W00-1317},
}
@inproceedings{data-restaurants-original,
author = {Ana-Maria Popescu, Oren Etzioni, and Henry Kautz},
title = {Towards a Theory of Natural Language Interfaces to Databases},
booktitle = {Proceedings of the 8th International Conference on Intelligent User Interfaces},
year = {2003},
location = {Miami, Florida, USA},
pages = {149--157},
url = {http://doi.acm.org/10.1145/604045.604070},
}
@inproceedings{data-restaurants,
author = {Alessandra Giordani and Alessandro Moschitti},
title = {Automatic Generation and Reranking of SQL-derived Answers to NL Questions},
booktitle = {Proceedings of the Second International Conference on Trustworthy Eternal Systems via Evolving Software, Data and Knowledge},
year = {2012},
location = {Montpellier, France},
pages = {59--76},
url = {https://doi.org/10.1007/978-3-642-45260-4_5},
}
spider 数据集——Text-to-SQL
需积分: 48 49 浏览量
2022-01-24
21:41:02
上传
评论 1
收藏 95.12MB ZIP 举报
spider 数据集——Text-to-SQL （399个子文件） 
lapTimes.csv 11.56MB results.csv 1.12MB driverStandings.csv 750KB qualifying.csv 308KB constructorStandings.csv 261KB constructorResults.csv 219KB pitStops.csv 216KB races.csv 102KB drivers.csv 78KB wine.csv 48KB Reservations.csv 38KB Reservations_t.csv 37KB flights.csv 25KB constructors.csv 15KB car-names.csv 13KB cars-data.csv 13KB circuits.csv 8KB airports100.csv 6KB seasons.csv 4KB appellations.csv 4KB status.csv 2KB list.csv 2KB Rooms.csv 627B car-makers.csv 588B model-list.csv 569B airlines.csv 481B grapes.csv 450B teachers.csv 323B countries.csv 248B continents.csv 80B cars.desc 4KB .DS_Store 6KB train_spider.json 23.77MB train_others.json 8.12MB dev.json 3.46MB tables.json 792KB world_1.json 7KB car_1.json 6KB flight_2.json 4KB annotation.json 3KB annotation.json 2KB annotation.json 2KB annotation.json 2KB annotation.json 1KB annotation.json 65B annotation.json 65B change_date.py 696B formula_1.splite 0B schema.sql 307.15MB schema.sql 54.94MB schema.sql 3.05MB schema.sql 2.42MB TextBookExampleSchema.sql 2.22MB schema.sql 1.57MB train_gold.sql 1.12MB dev_gold.sql 121KB schema.sql 51KB schema.sql 35KB schema.sql 34KB schema.sql 34KB schema.sql 31KB schema.sql 31KB schema.sql 30KB schema.sql 28KB schema.sql 27KB schema.sql 27KB schema.sql 26KB schema.sql 26KB schema.sql 21KB schema.sql 21KB schema.sql 21KB schema.sql 20KB schema.sql 20KB schema.sql 20KB schema.sql 19KB schema.sql 19KB schema.sql 18KB schema.sql 18KB schema.sql 17KB schema.sql 16KB schema.sql 16KB schema.sql 16KB schema.sql 16KB schema.sql 16KB schema.sql 15KB schema.sql 14KB schema.sql 14KB schema.sql 13KB schema.sql 13KB schema.sql 13KB schema.sql 12KB schema.sql 12KB schema.sql 11KB schema.sql 11KB schema.sql 10KB TinyCollege.sql 10KB schema.sql 10KB schema.sql 10KB schema.sql 9KB schema.sql 8KB共 399 条
- 1
- 2
- 3
- 4
评论0