Zhang, Jie;
Harman, mark;
(2022)
Leveraging Automated Unit Tests for Unsupervised Code Translation.
In:
Proceedings of The Tenth International Conference on Learning Representations: ICLR 2022.
ICLR: Virtual conference.
Preview |
PDF
UnitTests (1).pdf - Published Version Download (1MB) | Preview |
Abstract
With little to no parallel data available for programming languages, unsupervised methods are well-suited to source code translation. However, the majority of unsupervised machine translation approaches rely on back-translation, a method developed in the context of natural language translation and one that inherently involves training on noisy inputs. Unfortunately, source code is highly sensitive to small changes; a single token can result in compilation failures or erroneous programs, unlike natural languages where small inaccuracies may not change the meaning of a sentence. To address this issue, we propose to leverage an automated unit-testing system to filter out invalid translations, thereby creating a fully tested parallel corpus. We found that fine-tuning an unsupervised model with this filtered data set significantly reduces the noise in the translations so-generated, comfortably outperforming the state-of-the-art for all language pairs studied. In particular, for Java→Python and Python→C++ we outperform the best previous methods by more than 16% and 24% respectively, reducing the error rate by more than 35%.
| Type: | Proceedings paper |
|---|---|
| Title: | Leveraging Automated Unit Tests for Unsupervised Code Translation |
| Event: | The Tenth International Conference on Learning Representations |
| Dates: | 25 Apr 2022 - 29 Apr 2022 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://openreview.net/pdf?id=cmt-6KtR4c4 |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | unsupervised, translation, code, self-training, pseudo-labelling, unit tests, programming languages, deep learning, transformer |
| UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10149501 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
