While efforts have been made to explain computer vision models, these approaches often fall short of providing direct and human-understandable explanations.

Program translation isanimportant tool tomigrate legacycode inone 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.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

V anilla NA T model assumes that the target tokens are independent of each other given the source sentence. This assumption enables the parallel generation of all tokens.

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.

This makes parsing intractable and requires image grammars to be severely restricted in practice, for example by allowing only rectangular regions.