Quality Estimation & Interpretability for Code Translation

Mayank Agarwal, Kartik Talamadupula, Stephanie Houde, Fernando Martinez, Michael Muller, John Richards, Steven Ross, Justin Weisz

Keywords: machine translation, neural machine translation, code translation, ai for code, computer assisted programming, translation, machine learning, natural language processing, hci, human computer interaction

TL;DR: We try to correlate the confidences produced by a code translation model with lint errors in the translated code

Abstract: Recently, the automated translation of source code from one programming language to another by using automatic approaches inspired by Neural Machine Translation (NMT) methods for natural languages has come under study. However, such approaches suffer from the same problem as previous NMT approaches on natural languages, viz. the lack of an ability to estimate and evaluate the quality of the translations; and consequently ascribe some measure of interpretability to the model’s choices. In this paper, we attempt to estimate the quality of source code translations built on top of the TransCoder model. We consider the code translation task as an analog of machine translation for natural languages, with some added caveats. We present our main motivation from a user study built around code translation; and present a technique that correlates the confidences generated by that model to lint errors in the translated code. We conclude with some observations on these correlations, and some ideas for future work.