paper-with-me

Papers

Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations

2023-11-13 · Zilu Tang, Mayank Agarwal, Alex Shypula, Bailin Wang, Derry Wijaya, Jie Chen, Yoon Kim

This work explores the use of self-generated natural language explanations as an intermediate step for code-to-code translation with language models. Across three types of explanations and 19 programming languages constructed from the MultiPL-E dataset, we find the explanations to be particularly effective in the zero-shot case, improving performance by 12% on average. Improvements with natural language explanations are particularly pronounced on difficult programs. We release our dataset, code, and canonical solutions in all 19 languages.

📄 PDF Abstract BibTeX arXiv:2311.07070

Code (1)

pootiet/explain-then-translate 공식 구현 pytorch

Tasks

Code TranslationTranslation

Similar Papers 제목 키워드 기반

AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation

2024-10-31 · Ali Reza Ibrahimzada, Kaiyao Ke, Mrigank Pawagi, Muhammad Salman Abid 외

Code translation transforms programs from one programming language (PL) to another. Several rule-based transpilers have been designed to automate code translation between different pairs of PLs. However, the rules can be…

Code TranslationTranslation

Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis

2024-12-18 · Manish Shetty, Naman jain, Adwait Godbole, Sanjit A. Seshia 외

Despite extensive usage in high-performance, low-level systems programming applications, C is susceptible to vulnerabilities due to manual memory management and unsafe pointer operations. Rust, a modern systems programmi…

Code GenerationCode TranslationTranslation

A Case Study: Exploiting Neural Machine Translation to Translate CUDA to OpenCL

2019-05-18 · Yonghae Kim, Hyesoon Kim

The sequence-to-sequence (seq2seq) model for neural machine translation has significantly improved the accuracy of language translation. There have been new efforts to use this seq2seq model for program language translat…

GPUMachine TranslationTranslation

Evaluation of Google Translate for Mandarin Chinese translation using sentiment and semantic analysis

2024-09-08 · Xuechun Wang, Rodney Beard, Rohitash Chandra

Machine translation using large language models (LLMs) is having a significant global impact, making communication easier. Mandarin Chinese is the official language used for communication by the government and media in C…

Machine TranslationSentiment AnalysisTranslation

Neuro-Symbolic Bi-Directional Translation -- Deep Learning Explainability for Climate Tipping Point Research

2023-06-19 · Chace Ashcraft, Jennifer Sleeman, Caroline Tang, Jay Brett 외

In recent years, there has been an increase in using deep learning for climate and weather modeling. Though results have been impressive, explainability and interpretability of deep learning models are still a challenge.…

DecoderDeep Learning