Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning
This work addresses the challenge of balancing performance in code-related tasks for developers and researchers, though it is incremental as it builds on existing multi-task learning approaches.
The paper tackled the problem of jointly improving code retrieval and summarization by proposing an end-to-end model that leverages code generation and dual learning, resulting in significant improvements in code retrieval over state-of-the-art models and competitive performance in code summarization on SQL and Python datasets.
Code summarization generates brief natural language description given a source code snippet, while code retrieval fetches relevant source code given a natural language query. Since both tasks aim to model the association between natural language and programming language, recent studies have combined these two tasks to improve their performance. However, researchers have yet been able to effectively leverage the intrinsic connection between the two tasks as they train these tasks in a separate or pipeline manner, which means their performance can not be well balanced. In this paper, we propose a novel end-to-end model for the two tasks by introducing an additional code generation task. More specifically, we explicitly exploit the probabilistic correlation between code summarization and code generation with dual learning, and utilize the two encoders for code summarization and code generation to train the code retrieval task via multi-task learning. We have carried out extensive experiments on an existing dataset of SQL and Python, and results show that our model can significantly improve the results of the code retrieval task over the-state-of-art models, as well as achieve competitive performance in terms of BLEU score for the code summarization task.