UniCoR: Modality Collaboration for Robust Cross-Language Hybrid Code Retrieval
By: Yang Yang , Li Kuang , Jiakun Liu and more
Potential Business Impact:
Finds code faster using words and examples.
Effective code retrieval is indispensable and it has become an important paradigm to search code in hybrid mode using both natural language and code snippets. Nevertheless, it remains unclear whether existing approaches can effectively leverage such hybrid queries, particularly in cross-language contexts. We conduct a comprehensive empirical study of representative code models and reveal three challenges: (1) insufficient semantic understanding; (2) inefficient fusion in hybrid code retrieval; and (3) weak generalization in cross-language scenarios. To address these challenges, we propose UniCoR, a novel self-supervised framework that learns Unified Code Representations framework designed to learn unified and robust code representations. Firstly, we design a multi-perspective supervised contrastive learning module to enhance semantic understanding and modality fusion. It aligns representations from multiple perspectives, including code-to-code, natural language-to-code, and natural language-to-natural language, enforcing the model to capture a semantic essence among modalities. Secondly, we introduce a representation distribution consistency learning module to improve cross-language generalization, which explicitly aligns the feature distributions of different programming languages, enabling language-agnostic representation learning. Extensive experiments on both empirical benchmark and large-scale benchmark show that UniCoR outperforms all baseline models, achieving an average improvement of 8.64% in MRR and 11.54% in MAP over the best-performing baseline. Furthermore, UniCoR exhibits stability in hybrid code retrieval and generalization capability in cross-language scenarios.
Similar Papers
UniMoCo: Unified Modality Completion for Robust Multi-Modal Embeddings
CV and Pattern Recognition
Helps computers understand mixed text and picture questions.
M3DR: Towards Universal Multilingual Multimodal Document Retrieval
Information Retrieval
Finds information in documents across many languages.
CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval
Software Engineering
Helps find better, safer computer code.