Pangea: A Workbench for Statically Analyzing Multi-language Software Corpora.

Andrea Caracciolo Andrei Chis Boris Spasojevic Mircea Lungu

Published in: SCAM (2014)

Keyphrases

software development
modeling language
programming language
language learning
software systems
linguistic resources
software design

highly modular
comparable corpora
machine learning
computer systems
database
parallel corpus
english language

software package
software tools
software projects
software engineering
software architecture
software maintenance
user interface

natural language
text corpora
information systems
natural language processing
linguistic patterns
source code