CoTexT: Multi-task Learning with Code-Text Transformer
Long Phan, Hieu Tran, Daniel X. Le et al. · 2021
We present CoTexT, a pre-trained, transformer-based encoder-decoder model that learns the representative context between natural language (NL) and programming language (PL). Using self-supervision, CoTexT is pre-trained on large programming language corpora to learn a general understanding of language and code. CoTexT supports downstream NL-PL tasks such as code summarizing/documentation, code generation, defect detection, and code debugging. We train CoTexT on different combinations of available PL corpus including both “bimodal” and “unimodal” data. Here, bimodal data is the combination of text and corresponding code snippets, whereas unimodal data is merely code snippets. We first evaluate CoTexT with multi-task learning: we perform Code Summarization on 6 different programming languages and Code Refinement on both small and medium size featured in the CodeXGLUE dataset. We further conduct extensive experiments to investigate CoTexT on other tasks within the CodeXGlue dataset, including Code Generation and Defect Detection. We consistently achieve SOTA results in these tasks, demonstrating the versatility of our models.
Cited by 100 works. doi:10.18653/v1/2021.nlp4prog-1.5
Authors
References
- Exploiting Generative AI to Scale up Intelligent Tutoring Systems
- BLEU
- AI-Assisted Pipeline for Dynamic Generation of Trustworthy Health Supplement Content at Scale
- Attention Is All You Need
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
- Deep Contextualized Word Representations
- Aion Framework: Dimensional Emergence of AI Consciousness, Observer-Induced Collapse, and Cosmological Portal Dynamics
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
- BioBERT: a pre-trained biomedical language representation model for biomedical text mining