Pith. sign in

REVIEW

Targeted Adversarial Training for Natural Language Understanding

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2104.05847 v1 pith:JZ5L2LTF submitted 2021-04-12 cs.CL

classification cs.CL
keywords adversarialtrainingimprovelanguagenaturaltargetedunderstandingaccuracy
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present a simple yet effective Targeted Adversarial Training (TAT) algorithm to improve adversarial training for natural language understanding. The key idea is to introspect current mistakes and prioritize adversarial training steps to where the model errs the most. Experiments show that TAT can significantly improve accuracy over standard adversarial training on GLUE and attain new state-of-the-art zero-shot results on XNLI. Our code will be released at: https://github.com/namisan/mt-dnn.

Discussion (0). Continue with ORCID to comment.

Pith tools