Analyzing the Entire Program: Applying Natural Language Processing to Software Engineering

Subscribers:
351,000
Published on ● Video Link: https://www.youtube.com/watch?v=_bCMjacjSGQ



Duration: 1:06:52
952 views
17


A powerful, but limited, way to view software is as source code alone. Mathematical techniques, such as abstract interpretation and model checking, can indicate whether the program satisfies a formal specification. But, where does the formal specification come from? A program consists of much more than a sequence of instructions. Developers make use of test cases, documentation, variable names, program structure, the version control repository, and more. I argue that it is time to take the blinders off of software analysis tools: tools should use all these artifacts to deduce more powerful and useful information about the program. Researchers are beginning to make progress towards this vision. In this talk, I will discuss four initial results that find bugs and generate code, by making use of variable names, error messages, procedure documentation, and user questions.

See more on this video at https://www.microsoft.com/en-us/research/video/analyzing-entire-program-applying-natural-language-processing-software-engineering/




Other Videos By Microsoft Research


2017-01-30Programming by Examples (PBE): Flash Fill Extensions
2017-01-30Programming by Examples (PBE): Flash Fill
2017-01-30Programming by Examples (PBE): FlashExtract Video 2
2017-01-30Programming by Natural Language: Bing enabled code search
2017-01-27Towards Practical Machine Learning with Differential Privacy and Beyond
2017-01-27Learning Language through Interaction
2017-01-27Quantum Algorithms for Number Theory and their Relevance to Cryptography
2017-01-23Multivariate Set Tests for Genetic Association Studies
2017-01-17Convenient (and Collaborative) Audiovisual Media
2017-01-17Characterization of OLTP Workloads: from Micro-architecture to Power/Performance
2017-01-17Analyzing the Entire Program: Applying Natural Language Processing to Software Engineering
2017-01-17Biomarker Discovery in Personalized Medicine
2017-01-15Dr. Harry Shum on the future of AI at the 2017 Future Forum Annual Conference
2017-01-13International Workshop on Spoken Language Translation (IWSLT) 2016 - Session 3
2017-01-13A Translation NGO's View on Language Technology Trends
2017-01-13Multi-kernel Linear Mixed Models for Complex Phenotype Prediction
2017-01-13Higher Fidelity Systems for End-User Information Management
2017-01-11Specializing Shaders
2017-01-11Multiparty Turn Taking in Situated Dialog: Study, Lessons, and Directions - sample2-full-overhead
2017-01-11Facilitating Multiparty Dialog with Gaze, Gesture, and Speech - sample1-segment-scene
2017-01-11Facilitating Multiparty Dialog with Gaze, Gesture, and Speech - sample1-segment-overhead



Tags:
microsoft research