Yesterday, my program worked. Today, it does not. Why?
ESEC/FSE-7 Proceedings of the 7th European software engineering conference held jointly with the 7th ACM SIGSOFT international symposium on Foundations of software engineering
Toward natural language computation
Computational Linguistics
Jungloid mining: helping to navigate the API jungle
Proceedings of the 2005 ACM SIGPLAN conference on Programming language design and implementation
Locating faults through automated predicate switching
Proceedings of the 28th international conference on Software engineering
Pegasus: first steps toward a naturalistic programming language
Companion to the 21st ACM SIGPLAN symposium on Object-oriented programming systems, languages, and applications
SNIFF: A Search Engine for Java Using Free-Form Queries
FASE '09 Proceedings of the 12th International Conference on Fundamental Approaches to Software Engineering: Held as Part of the Joint European Conferences on Theory and Practice of Software, ETAPS 2009
Automatically finding patches using genetic programming
ICSE '09 Proceedings of the 31st International Conference on Software Engineering
Hi-index | 0.00 |
Despite years of work on programming languages, programming is still slow and error-prone. In this paper we describe Macho, a system which combines a natural language parser, a database of code, and an automated debugger to write simple programs from natural language and examples of their correct execution. Adding examples to natural language makes it easier for Macho to actually generate a correct program, because it can test its candidate solutions and fix simple errors. Macho is able to synthesize basic versions of six out of nine small coreutils from short natural language descriptions based on their man pages and sample runs.