Timezone: »

 
Oral
Open Vocabulary Learning on Source Code with a Graph-Structured Cache
Milan Cvitkovic · Badal Singh · Anima Anandkumar

Wed Jun 12 04:40 PM -- 05:00 PM (PDT) @ Room 102
in Networks and Relational Learning »

Machine learning models that take computer program source code as input typically use Natural Language Processing (NLP) techniques. However, a major challenge is that code is written using an open, rapidly changing vocabulary due to, e.g., the coinage of new variable and method names. Reasoning over such a vocabulary is not something for which most NLP methods are designed. We introduce a Graph-Structured Cache to address this problem; this cache contains a node for each new word the model encounters with edges connecting each word to its occurrences in the code. We find that combining this graph-structured cache strategy with recent Graph-Neural-Network-based models for supervised learning on code improves the models' performance on a code completion task and a variable naming task --- with over 100% relative improvement on the latter --- at the cost of a moderate increase in computation time.

[ Slides]  [ Video] 

Author Information

Milan Cvitkovic (California Institute of Technology)
Badal Singh (Amazon Web Services)
Anima Anandkumar (Caltech)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors