Neural Code Search Revisited: Enhancing Code Snippet Retrieval through Natural Language Intent
This addresses code search efficiency for developers, though it appears incremental as it builds on existing transfer learning and NLP techniques.
The paper tackles the problem of retrieving relevant code snippets using natural language queries by leveraging code descriptions to better capture intent. Their domain-specific retrieval model achieved absolute gains of up to 20.6% in mean reciprocal rank compared to state-of-the-art methods that use only unannotated code.
In this work, we propose and study annotated code search: the retrieval of code snippets paired with brief descriptions of their intent using natural language queries. On three benchmark datasets, we investigate how code retrieval systems can be improved by leveraging descriptions to better capture the intents of code snippets. Building on recent progress in transfer learning and natural language processing, we create a domain-specific retrieval model for code annotated with a natural language description. We find that our model yields significantly more relevant search results (with absolute gains up to 20.6% in mean reciprocal rank) compared to state-of-the-art code retrieval methods that do not use descriptions but attempt to compute the intent of snippets solely from unannotated code.