CoaCor: Code Annotation for Code Retrieval with Reinforcement Learning

Abstract

To accelerate software development, much research has been performed to help people understand and reuse the huge amount of available code resources. Two important tasks have been widely studied: code retrieval, which aims to retrieve code snippets relevant to a given natural language query from a code base, and code annotation, where the goal is to annotate a code snippet with a natural language description. Despite their advancement in recent years, the two tasks are mostly explored separately. In this work, we investigate a novel perspective of Code annotation for Code retrieval (hence called "CoaCor"), where a code annotation model is trained to generate a natural language annotation that can represent the semantic meaning of a given code snippet and can be leveraged by a code retrieval model to better distinguish relevant code snippets from others. To this end, we propose an effective framework based on reinforcement learning, which explicitly encourages the code annotation model to generate annotations that can be used for the retrieval task. Through extensive experiments, we show that code annotations generated by our framework are much more detailed and more useful for code retrieval, and they can further improve the performance of existing code retrieval models significantly. 1

Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning

“…For example, the BLEU score [24] of the code summarization model in CoaCor is not satisfactory though it improves the performance of existing code retrieval models significantly. Different from what claimed in [34], we respectively argue that generating summaries close to human-provided queries is naturally fit to code retrieval. The compromise of BLEU score, which represents the similarity between the generated summaries and human-written ones, can be avoided if we can model the inner connection between the two tasks better.…”

“…Two VAEs are trained jointly to reconstruct their inputs as much as possible with regularization that captures the closeness between the latent variables of code and description, which will be used for measuring similarity. Similarly, Yao et al [34] constructed a neural networkbased code annotation model to describe the functionality of an entire code snippet. It produces meaningful words that can be used for code retrieval where these words and a natural language query are projected into a vector space to measure the cosine similarity between them.…”

“…Both VAEs are trained jointly to reconstruct their inputs with regularization that captures the closeness between the latent variables of code and description. CoaCor [34] trained a code summarization model to generate code summaries that can be used for the retrieval task based on reinforcement learning. These approaches, however, have yet effectively leveraged the intrinsic connection between the two tasks.…”

FACER: An API Usage-based Code-example Recommender for Opportunistic Reuse

“…Several of the latest code search techniques that find code given a natural language query rely on machine learning techniques (e.g.,NCS [10], DeepCS [8], UNIF [38], MMAN [39], TBCAA [40], and CoaCor [41]). NCS proposes an enhanced word embedding for a natural language query [10].…”

“…This technique aims to capture semantics by incorporating API call information into ASTs which is otherwise abstracted as the same AST node type. CoaCor [41] uses reinforcement learning to build a code annotation framework for effective code retrieval. By generating detailed code annotations using multiple keywords, CoaCor improves the performance of existing code retrieval models.…”