Explore the concept of patching as translation in software engineering through this conference talk from ASE2020. Dive into the parallels between code patching and neural machine translation, examining data collection methods and task design considerations. Learn about the role of context and the impact of ambiguity in patch generation. Discover the architectural design of a seq2seq model for patching and gain insights into this innovative approach to software maintenance and bug fixing.
Patching as Translation: The Data and the Metaphor
Association for Computing Machinery (ACM) via YouTube
Overview
Syllabus
Intro
What is Patching?
What is Neural Machine Translation (NMT)?
Data Collection
Patching as Translation: Task Design
Task Design: Role of Context
Task Design: Impact of Ambiguity
Architectural Design
Seq2seq Model For Patching
Questions?
Taught by
Association for Computing Machinery (ACM)
Related Courses
-
Natural Language Generation in Python
-
Data Creation and Collection for Artificial Intelligence via Crowdsourcing
-
CMU Multilingual NLP 2022 - Translation and Translation Data
-
Challenges and Opportunities in Applying Machine Learning - Alex Jaimes - ODSC East 2018
-
Deep Learning and Software Engineering - A Retrospective and Paths Forward
-
Why Data Scientists Should Learn Software Engineering Principles
