PanGu-Coder: Program Synthesis with Function-Level Language Modeling

• URL: http://arxiv.org/abs/2207.11280v1
• Date: Fri, 22 Jul 2022 18:08:16 GMT
• Title: PanGu-Coder: Program Synthesis with Function-Level Language Modeling
• Authors: Fenia Christopoulou, Gerasimos Lampouras, Milan Gritta, Guchun Zhang, Yinpeng Guo, Zhongqi Li, Qi Zhang, Meng Xiao, Bo Shen, Lin Li, Hao Yu, Li Yan, Pingyi Zhou, Xin Wang, Yuchi Ma, Ignacio Iacobacci, Yasheng Wang, Guangtai Liang, Jiansheng Wei, Xin Jiang, Qianxiang Wang, Qun Liu
• Abstract summary: PanGu-Coder is a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation. We train PanGu-Coder using a two-stage strategy: the first stage employs Causal Language Modelling to pre-train on raw programming language data. The second stage uses a combination of Causal Language Modelling and Masked Language Modelling to train on loosely curated pairs of natural language program definitions and code functions.
• Score: 47.63943623661298
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i.e. the synthesis of programming language solutions given a natural language problem description. We train PanGu-Coder using a two-stage strategy: the first stage employs Causal Language Modelling (CLM) to pre-train on raw programming language data, while the second stage uses a combination of Causal Language Modelling and Masked Language Modelling (MLM) training objectives that focus on the downstream task of text-to-code generation and train on loosely curated pairs of natural language program definitions and code functions. Finally, we discuss PanGu-Coder-FT, which is fine-tuned on a combination of competitive programming problems and code with continuous integration tests. We evaluate PanGu-Coder with a focus on whether it generates functionally correct programs and demonstrate that it achieves equivalent or better performance than similarly sized models, such as CodeX, while attending a smaller context window and training on less data.

Related papers

• NoviCode: Generating Programs from Natural Language Utterances by Novices [59.71218039095155]
  We present NoviCode, a novel NL Programming task which takes as input an API and a natural language description by a novice non-programmer. We show that NoviCode is indeed a challenging task in the code synthesis domain, and that generating complex code from non-technical instructions goes beyond the current Text-to-Code paradigm.
  arXiv  Detail & Related papers  (2024-07-15T11:26:03Z)
• Synthetic Programming Elicitation for Text-to-Code in Very Low-Resource Programming and Formal Languages [21.18996339478024]
  We introduce emphsynthetic programming elicitation and compilation (SPEAC) SPEAC produces syntactically correct programs more frequently and without sacrificing semantic correctness. We empirically evaluate the performance of SPEAC in a case study for the UCLID5 formal verification language.
  arXiv  Detail & Related papers  (2024-06-05T22:16:19Z)
• CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation [58.84212778960507]
  We propose CodeGRAG, a Graphical Retrieval Augmented Code Generation framework to enhance the performance of LLMs. CodeGRAG builds the graphical view of code blocks based on the control flow and data flow of them to fill the gap between programming languages and natural language. Various experiments and ablations are done on four datasets including both the C++ and python languages to validate the hard meta-graph prompt, the soft prompting technique, and the effectiveness of the objectives for pretrained GNN expert.
  arXiv  Detail & Related papers  (2024-05-03T02:48:55Z)
• IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators [49.903001442804594]
  This work investigates the prospect of leveraging compiler intermediate representations (IR) to improve the multilingual capabilities of Code-LMs. We first compile SLTrans, a parallel dataset consisting of nearly 4M self-contained source code files. Next, we carry out continued causal language modelling training on SLTrans, forcing the Code-LMs to learn the IR language. Our resulting models, dubbed IRCoder, display sizeable and consistent gains across a wide variety of code generation tasks and metrics.
  arXiv  Detail & Related papers  (2024-03-06T17:52:08Z)
• A Conversational Paradigm for Program Synthesis [110.94409515865867]
  We propose a conversational program synthesis approach via large language models. We train a family of large language models, called CodeGen, on natural language and programming language data. Our findings show the emergence of conversational capabilities and the effectiveness of the proposed conversational program synthesis paradigm.
  arXiv  Detail & Related papers  (2022-03-25T06:55:15Z)
• Synchromesh: Reliable code generation from pre-trained language models [38.15391794443022]
  We propose Synchromesh: a framework for substantially improving the reliability of pre-trained models for code generation. First, it retrieves few-shot examples from a training bank using Target Similarity Tuning (TST), a novel method for semantic example selection. Then, Synchromesh feeds the examples to a pre-trained language model and samples programs using Constrained Semantic Decoding (CSD), a general framework for constraining the output to a set of valid programs in the target language.
  arXiv  Detail & Related papers  (2022-01-26T22:57:44Z)
• Unified Pre-training for Program Understanding and Generation [46.89905110678675]
  PLBART is a sequence-to-sequence model capable of performing a broad spectrum of program and language understanding and generation tasks. PLBART is pre-trained on an extensive collection of Java and Python functions and associated NL text via denoising autoencoding.
  arXiv  Detail & Related papers  (2021-03-10T20:32:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.