Spider 1.0

Spider is a large-scale complex and cross-domain semantic parsing and text-to-SQL dataset annotated by 11 Yale students. The goal of the Spider challenge is to develop natural language interfaces to cross-domain databases. It consists of 10,181 questions and 5,693 unique complex SQL queries on 200 databases with multiple tables covering 138 different domains. In Spider 1.0, different complex SQL queries and databases appear in train and test sets. To do well on it, systems must generalize well to not only new SQL queries but also new database schemas.

---

Why we call it "Spider"? It is because our dataset is complex and cross-domain like a spider crawling across mutiple complex(with many foreign keys) nests(databases). Spider Paper (EMNLP'18) Spider Post

---

Related challenges: multi-turn SParC and conversational CoSQL text-to-SQL tasks. SParC Challenge (ACL'19) CoSQL Challenge (EMNLP'19)

• 01/16/2020 For value prediction (in order to compute the execution accuracy), your model should be able to 1) copy from the question inputs, 2) retrieve from the database content (database content is available), or 3) generate numbers (e.g. 3 in "LIMIT 3").
• 9/24/2019 (Min et al., EMNLP 2019) translated Spider to Chinese! Check out the Chinese challenge page.
• 5/17/2019 Our paper SParC: Cross-Domain Semantic Parsing in Context with Salesforce Research was accepted to ACL 2019! It introduces the context-dependent version of the Spider challenge: SParC!
• 5/17/2019 Please report any annotation errors here, we really appreciate your help and will update the data release in this summer!
• 1/14/2019 The submission tutorial is out!.
• 12/17/2018 We updated 7 sqlite database files (issue 14). Please download the Spider dataset from this page again.
• 10/25/2018 The evaluation script and results were updated (issue 5). Please download the lastest versions of the script and papers. Also, please follow instructions in issue 3 to generate the latest SQL parsing results (fixed a bug).

As the above spider chart shows, Spider 1.0 is distinct from most of the previous semantic parsing tasks because:

• ATIS, Geo, Academic: Each of them contains only a single database with a limited number of SQL queries, and has exact same SQL queries in train and test splits.
• WikiSQL: The numbers of SQL queries and tables are significantly large. But all SQL queries are simple, and each database is only a simple table without any foreign key.

Spider 1.0 spans the largest area in the chart, making it the first complex and cross-domain semantic parsing and text-to-SQL dataset! Read more on the blog post.

The data is split into training, development, and unreleased test sets. Download a copy of the dataset (distributed under the CC BY-SA 4.0 license):

Once you have built a model that works to your expectations on the dev set, you can submit it to get official scores on the dev and a hidden test set. To preserve the integrity of test results, we do not release the test set to the public. Instead, we request you to submit your model so that we can run it on the test set for you. Here's a tutorial walking you through official evaluation of your model:

Some examples look like the following:

Ask us questions at our Github issues page or contact Tao Yu, Rui Zhang, or Michihiro Yasunaga.

We expect the dataset to evolve. We would greatly appreciate it if you could donate us your non-private databases or SQL queries for the project.

We thank Graham Neubig, Tianze Shi, Catherine Finegan-Dollak, and the anonymous reviewers for their precious comments on this project. Also, we thank Pranav Rajpurkar for giving us the permission to build this website based on SQuAD.

Our team at the summit of the East Rock park in New Haven (The pose is "NLseq2SQL"):

For exact matching evaluation, instead of simply conducting string comparison between the predicted and gold SQL queries, we decompose each SQL into several clauses, and conduct set comparison in each SQL clause. Please refer to the paper and the Github page for more details.

Other papers used Spider (evaluated on the dev but not test set):

1. (Min et al., EMNLP 2019), Westlake University, Spider in Chinese
2. (Yao et al., EMNLP 2019), OSU & Facebook AI Research
3. (Shaw et al., ACL 2019), Google
4. (Shin et al., NeurlPS 2019), UC Berkeley & MSR
5. (Weir et al., SIGMOD 2019), Brown University & TU Darmstadt
6. (Baik et al., ICDE 2019), U of Michigan & IBM

Our current models do not predict any value in SQL conditions so that we do not provide execution accuracies. However, we encourage you to provide it in the future submissions. For value prediction, For value prediction, your model should be able to 1) copy from the question inputs, 2) retrieve from the database content (database content is available), or 3) generate numbers (e.g. 3 in "LIMIT 3").

For comparison, the models achieve much higher results if we split the dataset based on data examples instead of databases since the systems don't need to generalize to new database schemas.