Incorporating External Knowledge through Pre-training for Natural Language to Code Generation
This work addresses code generation for developers by enhancing performance with external data, but it is incremental as it builds on existing methods.
The paper tackled the problem of generating code from natural language by incorporating external knowledge from StackOverflow and API documentation, achieving a 2.2% absolute BLEU score improvement on the CoNaLa benchmark.
Open-domain code generation aims to generate code in a general-purpose programming language (such as Python) from natural language (NL) intents. Motivated by the intuition that developers usually retrieve resources on the web when writing code, we explore the effectiveness of incorporating two varieties of external knowledge into NL-to-code generation: automatically mined NL-code pairs from the online programming QA forum StackOverflow and programming language API documentation. Our evaluations show that combining the two sources with data augmentation and retrieval-based data re-sampling improves the current state-of-the-art by up to 2.2% absolute BLEU score on the code generation testbed CoNaLa. The code and resources are available at https://github.com/neulab/external-knowledge-codegen.