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

Zilu Tang, Mayank Agarwal, Alex Shypula, Bailin Wang, Derry Wijaya +2 more
11/13/2023
cs.CL

No official code found. Best implementation: PootieT/explain-then-translate (29 stars, last commit 2023-12-05).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

PootieT/explain-then-translateCommunity100%

Official repo for EMNLP 2023 paper "Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations"

291C, C++Oct 22, 20232 years ago

Similar Papers

Exploring Data Augmentation for Code Generation Tasks

85% match2023

The Behavior of Large Language Models When Prompted to Generate Code Explanations

85% match2023

Synthetic Programming Elicitation for Text-to-Code in Very Low-Resource Programming and Formal Languages

85% match1 repo42026

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

84% match2022

VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation

84% match2026

Code Representation Pre-training with Complements from Program Executions

84% match2023

Cite this paper

@article{tang2023explainthentranslate,
  title  = {Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations},
  author = {Zilu Tang and Mayank Agarwal and Alex Shypula and Bailin Wang and Derry Wijaya and Jie Chen and Yoon Kim},
  year   = {2023},
  eprint = {2311.07070},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.07070v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.07070.svg)](https://codeofpaper.com/paper/2311.07070)

Discussion