paper-with-me

Papers

A Syntactic Neural Model for General-Purpose Code Generation

2017-04-06 · ACL 2017 7 · Pengcheng Yin, Graham Neubig

We consider the problem of parsing natural language descriptions into source code written in a general-purpose programming language like Python. Existing data-driven methods treat this problem as a language generation task without considering the underlying syntax of the target programming language. Informed by previous work in semantic parsing, in this paper we propose a novel neural architecture powered by a grammar model to explicitly capture the target syntax as prior knowledge. Experiments find this an effective way to scale up to generation of complex programs from natural language descriptions, achieving state-of-the-art results that well outperform previous code generation and semantic parsing approaches.

📄 PDF Abstract BibTeX arXiv:1704.01696

Code (6)

Peyvand-Andalibi/NL2Code
gsh2014/grammar-coarse2fine
pcyin/NL2code
pedrobragap/products_classification
yangkai2g7k/nl2code
zimengq/PyTorch-ReCode pytorch

Tasks

Code GenerationSemantic ParsingText Generation

Similar Papers 제목 키워드 기반

Type-Constrained Code Generation with Language Models

2025-04-12 · Niels Mündler, Jingxuan He, Hao Wang, Koushik Sen 외

Large language models (LLMs) have achieved notable success in code generation. However, they still frequently produce uncompilable output because their next-token inference procedure does not model formal aspects of code…

Code GenerationHumanEvalmbpp

Leveraging Partial Dependency Trees to Control Image Captions

2021-06-01 · NAACL (ALVR) 2021 6 · Wenjie Zhong, Yusuke Miyao

Controlling the generation of image captions attracts lots of attention recently. In this paper, we propose a framework leveraging partial syntactic dependency trees as control signals to make image captions include spec…

Image Captioning

CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code

2024-04-24 · Batu Guan, Yao Wan, Zhangqian Bi, Zheng Wang 외

Large Language Models (LLMs) have achieved remarkable progress in code generation. It now becomes crucial to identify whether the code is AI-generated and to determine the specific model used, particularly for purposes s…

Code GenerationDiversity

Enhancing the Transformer Decoder with Transition-based Syntax

2021-01-29 · Leshem Choshen, Omri Abend

Notwithstanding recent advances, syntactic generalization remains a challenge for text decoders. While some studies showed gains from incorporating source-side symbolic syntactic and semantic structure into text generati…

DecoderMachine TranslationText GenerationTranslation

LLM4CodeRE: Generative AI for Code Decompilation Analysis and Reverse Engineering

2026-04-07 · Hamed Jelodar, Samita Bai, Tochukwu Emmanuel Nwankwo, Parisa Hamedi 외 arxiv

Code decompilation analysis is a fundamental yet challenging task in malware reverse engineering, particularly due to the pervasive use of sophisticated obfuscation techniques. Although recent large language models (LLMs…