Imparting universal linguistic inductive biases via meta-learning

Language description:

Constraint ranking:

Set of consonants:

Set of vowels:

Consonant for insertion:

Vowel for insertion:

Input	Correct output	Meta-initialized model's output	Randomly-initialized model's output
rOau	.rO.a.u.	.rO.a.u.	.rO.a.u.
axxaO	.a.xa.O.	.a.xa.O.	.a.xa.O.
rxxa	.xa.	.xa.	.xa.
axrxu	.a.xu.	.a.xu.	.a.xu.
ttxaO	.xa.O.	.xa.O.	.xa.O.

Training examples seen:

Input	Correct output	Meta-initialized model's output	Randomly-initialized model's output
rOau	.rO.a.u.	.rO.a.u.	.rO.a.u.
axxaO	.a.xa.O.	.a.xa.O.	.a.xa.O.
rxxa	.xa.	.xa.	.xa.
axrxu	.a.xu.	.a.xu.	.a.xu.
ttxaO	.xa.O.	.xa.O.	.xa.O.

Training examples seen:

Use multiple tabs: Click on the type of generalization you want to study.

People can enter their own training set and test set and see how the model learns it.