Papers with large-scale code retrieval datasets
Adversarial Training for Code Retrieval with Question-Description Relevance Regularization (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for code retrieval are based on question-description relevance . code retrievals are a key task aiming to match natural and programming languages . |
| Approach: | They propose to use question-description relevance to regularize adversarial learning for code retrieval . they adapt a simple adversarial learning technique to generate difficult code snippets . |
| Outcome: | The proposed method can improve the performance of state-of-the-art models on large-scale code retrieval datasets of two programming languages. |