Pith. sign in

REVIEW

Disentangled Contrastive Learning for Learning Robust Textual Representations

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 2104.04907 v2 pith:PLYI2QF2 submitted 2021-04-11 cs.CL cs.AIcs.IRcs.LG

classification cs.CLcs.AIcs.IRcs.LG
keywords learningcontrastiverepresentationsresultstextualbenchmarksdisentangledobtain
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this process is still vulnerable to small and imperceptible permutations originating from legitimate inputs. Intuitively, the representations should be similar in the feature space with subtle input permutations, while large variations occur with different meanings. This motivates us to investigate the learning of robust textual representation in a contrastive manner. However, it is non-trivial to obtain opposing semantic instances for textual samples. In this study, we propose a disentangled contrastive learning method that separately optimizes the uniformity and alignment of representations without negative sampling. Specifically, we introduce the concept of momentum representation consistency to align features and leverage power normalization while conforming the uniformity. Our experimental results for the NLP benchmarks demonstrate that our approach can obtain better results compared with the baselines, as well as achieve promising improvements with invariance tests and adversarial attacks. The code is available in https://github.com/zxlzr/DCL.

Discussion (0). Continue with ORCID to comment.

Pith tools