A Joint Learning Model with Variational Interaction for Multilingual Program Translation

TL;DR

This paper introduces VIM-PT, a novel joint learning model that uses variational interaction to improve multilingual program translation by disentangling shared and language-specific features, effectively leveraging non-parallel data.

Contribution

It proposes a disentanglement-based generative approach for joint multilingual program translation, addressing data scarcity and semantic distribution shifts.

Findings

Improves translation quality by capturing shared information more accurately.

Leverages non-parallel data to enhance multilingual translation.

Reduces deployment complexity with a unified model.

Abstract

Programs implemented in various programming languages form the foundation of software applications. To alleviate the burden of program migration and facilitate the development of software systems, automated program translation across languages has garnered significant attention. Previous approaches primarily focus on pairwise translation paradigms, learning translation between pairs of languages using bilingual parallel data. However, parallel data is difficult to collect for some language pairs, and the distribution of program semantics across languages can shift, posing challenges for pairwise program translation. In this paper, we argue that jointly learning a unified model to translate code across multiple programming languages is superior to separately learning from bilingual parallel data. We propose Variational Interaction for Multilingual Program Translation~(VIM-PT), a disentanglement-based generative approach that jointly trains a unified model for multilingual program translation across multiple languages. VIM-PT disentangles code into language-shared and language-specific features, using variational inference and interaction information with a novel lower bound, then achieves program translation through conditional generation. VIM-PT demonstrates four advantages: 1) captures language-shared information more accurately from various implementations and improves the quality of multilingual program translation, 2) mines and leverages the capability of non-parallel data, 3) addresses the distribution shift of program semantics across languages, 4) and serves as a unified model, reducing deployment complexity.