Timezone: »

 
Poster
Tree-to-tree Neural Networks for Program Translation
Xinyun Chen · Chang Liu · Dawn Song

Tue Dec 04 07:45 AM -- 09:45 AM (PST) @ Room 210 #96
in Tue Poster Session A »

Program translation is an important tool to migrate legacy code in one language into an ecosystem built in a different language. In this work, we are the first to employ deep neural networks toward tackling this problem. We observe that program translation is a modular procedure, in which a sub-tree of the source tree is translated into the corresponding target sub-tree at each step. To capture this intuition, we design a tree-to-tree neural network to translate a source tree into a target one. Meanwhile, we develop an attention mechanism for the tree-to-tree model, so that when the decoder expands one non-terminal in the target tree, the attention mechanism locates the corresponding sub-tree in the source tree to guide the expansion of the decoder. We evaluate the program translation capability of our tree-to-tree model against several state-of-the-art approaches. Compared against other neural translation models, we observe that our approach is consistently better than the baselines with a margin of up to 15 points. Further, our approach can improve the previous state-of-the-art program translation approaches by a margin of 20 points on the translation of real-world projects.

Keywords: Structured Prediction · Attention Models · Recurrent Networks · Supervised Deep Networks

Author Information

Xinyun Chen (UC Berkeley)
Chang Liu (Citadel)
Dawn Song (UC Berkeley)

More from the Same Authors