Abstract
Existing supervised contrastive learning frameworks suffer from two major drawbacks: (i) they depend on labeled data, which is limited for the majority of tasks in real-world, and (ii) they incorporate inter-class relationships based on instance-level information, while ignoring corpus-level information, for weighting negative samples. To mitigate these challenges, we propose an effective distantly supervised contrastive learning framework (InfoDCL) that makes use of naturally occurring surrogate labels in the context of contrastive learning and employs pointwise mutual information to leverage corpus-level information. Our framework outperforms an extensive set of existing contrastive learning methods (self-supervised, supervised, and weakly supervised) on a wide range of social meaning tasks (in-domain and out-of-domain), in both the general and few-shot settings. Our method is also language-agnostic, as we demonstrate on three languages in addition to English.
Abstract (translated)
URL
https://arxiv.org/abs/2203.07648
