paper-with-me

Papers

Deep Reinforcement Learning for Programming Language Correction

2018-01-31 · Rahul Gupta, Aditya Kanade, Shirish Shevade

Novice programmers often struggle with the formal syntax of programming languages. To assist them, we design a novel programming language correction framework amenable to reinforcement learning. The framework allows an agent to mimic human actions for text navigation and editing. We demonstrate that the agent can be trained through self-exploration directly from the raw input, that is, program text itself, without any knowledge of the formal syntax of the programming language. We leverage expert demonstrations for one tenth of the training data to accelerate training. The proposed technique is evaluated on 6975 erroneous C programs with typographic errors, written by students during an introductory programming course. Our technique fixes 14% more programs and 29% more compiler error messages relative to those fixed by a state-of-the-art tool, DeepFix, which uses a fully supervised neural machine translation approach.

📄 PDF Abstract BibTeX arXiv:1801.10467

Code (1)

terne/dtuproject pytorch

Tasks

Deep Reinforcement LearningMachine TranslationProgram Repairreinforcement-learningReinforcement LearningReinforcement Learning (RL)Translation

Similar Papers 제목 키워드 기반

CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models

2023-09-05 · Lingyue Fu, Huacan Chai, Shuang Luo, Kounianhua Du 외

With the emergence of Large Language Models (LLMs), there has been a significant improvement in the programming capabilities of models, attracting growing attention from researchers. Evaluating the programming capabiliti…

Code GenerationMultiple-choice

Language-Conditioned Reinforcement Learning to Solve Misunderstandings with Action Corrections

2022-11-18 · Frank Röder, Manfred Eppe

Human-to-human conversation is not just talking and listening. It is an incremental process where participants continually establish a common understanding to rule out misunderstandings. Current language understanding me…

Instruction Followingreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Text-to-SQL Error Correction with Language Models of Code

2023-05-22 · Ziru Chen, Shijie Chen, Michael White, Raymond Mooney 외

Despite recent progress in text-to-SQL parsing, current semantic parsers are still not accurate enough for practical use. In this paper, we investigate how to build automatic text-to-SQL error correction models. Noticing…

SQL ParsingText to SQLText-To-SQL

Synthetic Error Injection Fails to Elicit Self-Correction In Language Models

2025-12-02 · David X. Wu, Shreyas Kapur, Anant Sahai, Stuart Russell arxiv

Reinforcement learning has become the dominant paradigm for eliciting reasoning and self-correction capabilities in large language models, but its computational expense motivates exploration of alternatives. Inspired by …

Reinforcement LearningAutonomous Driving

Grammatical Error Correction Using Integer Linear Programming

2013-08-01 · ACL 2013 8 · Yuanbin Wu, Hwee Tou Ng
Grammatical Error Correction