Thu 8 Nov 2018 10:52 - 11:15 at Horizons 6-9F - Repair and Synthesis Chair(s): Shahar Maoz

This paper targets the problem of speech act detection in conversations about bug repair. We conduct a ``Wizard of Oz'' experiment with 30 professional programmers, in which the programmers fix bugs for two hours, and use a simulated virtual assistant for help. Then, we use an open coding manual annotation procedure to identify the speech act types in the conversations. Finally, we train and evaluate a supervised learning algorithm to automatically detect the speech act types in the conversations. In 30 two-hour conversations, we made 2459 annotations and uncovered 26 speech act types. Our automated detection achieved 69% precision and 50% recall. The key application of this work is to advance the state of the art for virtual assistants in software engineering. Virtual assistant technology is growing rapidly, though applications in software engineering are behind those in other areas, largely due to a lack of relevant data and experiments. This paper targets this problem in the area of developer Q/A conversations about bug repair.

Thu 8 Nov
Times are displayed in time zone: Guadalajara, Mexico City, Monterrey change

10:30 - 12:00
Repair and SynthesisResearch Papers / Journal-First at Horizons 6-9F
Chair(s): Shahar MaozTel Aviv University
10:30
22m
Talk
Machine Learning-Based Prototyping of Graphical User Interfaces for Mobile Apps
Journal-First
Kevin MoranCollege of William & Mary, Carlos Bernal-CárdenasWilliam and Mary, Michael Curcio, Richard Bonett, Denys PoshyvanykWilliam and Mary
DOI Pre-print Media Attached
10:52
22m
Talk
Detecting Speech Act Types in Developer Question/Answer Conversations during Bug Repair
Research Papers
11:15
22m
Research paper
Visual Web Test Repair
Research Papers
Andrea StoccoUniversity of British Columbia, Rahulkrishna YandrapallyUniversity of British Columbia, Canada, Ali MesbahUniversity of British Columbia
Pre-print Media Attached
11:37
22m
Talk
Syntax-Guided Synthesis of Datalog Programs
Research Papers
Xujie SiUniversity of Pennsylvania, Woosuk LeeUniversity of Pennsylvania, USA, Richard ZhangUniversity of Pennsylvania, Aws AlbarghouthiUniversity of Wisconsin-Madison, Paraschos KoutrisUniversity of Wisconsin-Madison, USA, Mayur NaikUniversity of Pennsylvania