Recent work learns contextual representations of source code by reconstructing tokens from their context. For downstream semantic understanding tasks like code clone detection, these representations should ideally capture program functionality. However, we show that the popular reconstruction-based RoBERTa model is sensitive to source code edits, even when the edits preserve semantics. We propose ContraCode: a contrastive pre-training task that learns code functionality, not form. ContraCode pre-trains a neural network to identify functionally similar variants of a program among many non-equivalent distractors. We scalably generate these variants using an automated source-to-source compiler as a form of data augmentation. Contrastive pre-training outperforms RoBERTa on an adversarial code clone detection benchmark by 39% AUROC. Surprisingly, improved adversarial robustness translates to better accuracy over natural code; ContraCode improves summarization and TypeScript type inference accuracy by 2 to 13 percentage points over competitive baselines. All source is available at https://github.com/parasj/contracode.

We describe a connectionist model which learns to parse single sentences from sequential word input. A parse in the connectionist network contains information about role assignment, prepositional attachment, relative clause structure, and subordinate clause structure. The trained network displays several interesting types of behavior. These include predictive ability, tolerance to certain corruptions of input word sequences, and some generalization capability. We report on experiments in which a small number of sentence types have been successfully learned by a network. Work is in progress on a larger database. Application of this type of connectionist model to the area of spoken language processing is discussed.