Self Learning from Large Scale Code Corpus to Infer Structure of Method Invocations

TL;DR

This paper introduces MethodInfoToCode, a context-aware approach that leverages a large-scale code corpus and phrase-based statistical machine translation to accurately predict method invocation expressions from method names and surrounding context.

Contribution

It proposes a novel context-embedding method that improves code generation accuracy by combining large-scale code data with phrase-based statistical translation techniques.

Findings

Achieved 73% F1 score in expression prediction

Utilized 2.86 million method invocations from GitHub data

Improved accuracy over previous approaches

Abstract

Automatically generating code from a textual description of method invocation confronts challenges. There were two current research directions for this problem. One direction focuses on considering a textual description of method invocations as a separate Natural Language query and do not consider the surrounding context of the code. Another direction takes advantage of a practical large scale code corpus for providing a Machine Translation model to generate code. However, this direction got very low accuracy. In this work, we tried to improve these drawbacks by proposing MethodInfoToCode, an approach that embeds context information and optimizes the ability of learning of original Phrase-based Statistical Machine Translation (PBMT) in NLP to infer implementation of method invocation given method name and other context information. We conduct an expression prediction models learned from 2.86 million method invocations from the practical data of high qualities corpus on Github that used 6 popular libraries: JDK, Android, GWT, Joda-Time, Hibernate, and Xstream. By the evaluation, we show that if the developers only write the method name of a method invocation in a body of a method, MethodInfoToCode can predict the generated expression correctly at 73% in F1 score.