How far can we get by training Text-to-SQL models without any annotated SQL? Pretty far, it seems!

Our new work in Findings of #NAACL2022 with @JonathanBerant and Daniel Deutch


🧵 1/5
Text-to-SQL models should help non-experts easily query databases. But annotating examples to train them requires expertise (labeling NL utterances with SQL queries).

Can we train good enough models without any expert annotations?

Instead of gold SQL, we train text-to-SQL models on weak supervision: (1) answers & (2) question decompositions (annotated / predicted by a model) ⛏️

Using the database + question decomposition + answer we automatically synthesize a corresponding SQL query. This is well captured by mapping rules from the decomposition to SQL.

We test on five text-to-SQL benchmarks:
(1) Weakly supervised models reach ~94% of those trained on gold SQL
(2) Even models trained on few / zero in-domain decompositions still reach ~90% of the gold SQL ones

More results in our paper! 📃⚒️


• • •

Missing some Tweet in this thread? You can try to force a refresh

Keep Current with Tomer Wolfson

Tomer Wolfson Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!


Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!


0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy


3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!