APICom: Automatic API Completion via Prompt Learning and Adversarial Training-based Data Augmentation

TL;DR

APICom introduces a novel prompt learning and adversarial training approach for automatic API completion, significantly outperforming existing methods in generating accurate APIs from developer queries.

Contribution

The paper proposes APICom, a new API completion model leveraging prompt learning and adversarial data augmentation, addressing prefix information and improving generation accuracy.

Findings

APICom outperforms baselines by over 40% in EM@1.

Adversarial training improves model stability and accuracy.

Component ablations confirm the effectiveness of prompt learning and adversarial methods.

Abstract

Based on developer needs and usage scenarios, API (Application Programming Interface) recommendation is the process of assisting developers in finding the required API among numerous candidate APIs. Previous studies mainly modeled API recommendation as the recommendation task, which can recommend multiple candidate APIs for the given query, and developers may not yet be able to find what they need. Motivated by the neural machine translation research domain, we can model this problem as the generation task, which aims to directly generate the required API for the developer query. After our preliminary investigation, we find the performance of this intuitive approach is not promising. The reason is that there exists an error when generating the prefixes of the API. However, developers may know certain API prefix information during actual development in most cases. Therefore, we model this problem as the automatic completion task and propose a novel approach APICom based on prompt learning, which can generate API related to the query according to the prompts (i.e., API prefix information). Moreover, the effectiveness of APICom highly depends on the quality of the training dataset. In this study, we further design a novel gradient-based adversarial training method {\atpart} for data augmentation, which can improve the normalized stability when generating adversarial examples. To evaluate the effectiveness of APICom, we consider a corpus of 33k developer queries and corresponding APIs. Compared with the state-of-the-art baselines, our experimental results show that APICom can outperform all baselines by at least 40.02\%, 13.20\%, and 16.31\% in terms of the performance measures EM@1, MRR, and MAP. Finally, our ablation studies confirm the effectiveness of our component setting (such as our designed adversarial training method, our used pre-trained model, and prompt learning) in APICom.