08:15 – 08:30 PST Opening Remarks
08:30 – 08:55 PST "Conversational Machine Learning," Tom Mitchell (Carnegie Mellon)
09:00 – 09:25 PST "Intelligibility Throughout the Machine Learning Life Cycle," Jenn Wortman Vaughan (Microsoft Research)
09:30 – 09:55 PST "Learning from simple explanations," Sanjoy Dasgupta (UCSD)
10:00 – 10:25 PST "Towards Interpretable representation learning and evaluation," Finale Doshi-Velez (Harvard)
10:25 – 11:30 PST Q & A and Panel Session with Tom Mitchell, Jenn Wortman Vaughan, Sanjoy Dasgupta, and Finale Doshi-Velez
11:30 – 12:45 PST Poster Session 1
12:45 – 13:55 PST Break (Or meet on GatherTown)
14:00 – 14:25 PST "Optimizing human-AI teams," Dan Weld (AI2, University of Washington)
14:30 – 14:55 PST "People Watching for Learning Visual Affordances," Kristen Grauman (UT Austin, FAIR)
15:00 – 15:25 PST "Interactive Semantic Parsing for Question Answering," Scott Yih (FAIR)
15:30 – 15:55 PST "Assisting the human in decision making with interpretable, actionable AI suggestions," Emma Brunskill (Stanford)
16:00 – 16:25 PST "Programmatically managing training data for real-world ML," Alex Ratner (Snorkel, University of Washington)
16:25 – 17:30 PST Q & A and Panel Session with Dan Weld, Kristen Grauman, Scott Yih, Emma Brunskill, and Alex Ratner
17:30 – 18:45 PST Poster Session 2
18:45 – 19:00 PST Closing Remarks
19:00 – 20:00 PST Social/Get-Together on GatherTown

Poster Sessions

Session 1

1A Explanation Augmented Feedback in Human-in-the-Loop Reinforcement Learning (Lin Guan, Mudit Verma, Sihang Guo, Ruohan Zhang, Subbarao Kambhampati)
1B CoRefi: A Crowd Sourcing Suite for Coreference Annotation (Aaron Bornstein, Arie Cattan, Ido Dagan)
1C Conceptualization and Framework of Hybrid Intelligence Systems (Nikhil Prakash, Kory Wallace Mathewson)
1D Continuous and Interactive Factual Knowledge Learning in Verification Dialogues (Sahisnu Mazumder, Bing Liu, Nianzu Ma, Shuai Wang)
1E Robust Active Learning Strategies for Model Variability (José Mena Roldán, Matthias Gallé)
1F MEME: Generating RNN Model Explanations via Model Extraction (Dmitry Kazhdan, Botty Dimanov, Mateja Jamnik, Pietro Liò)
1G The Reverse Turing Test for Evaluating Interpretability Methods on Unknown Tasks (Ana Gonzalez, Anders Søgaard)
1H Accounting for Human Learning when Inferring Human Preferences (Harry Giles, Lawrence Chan)
1I Value Alignment Verification (Daniel S. Brown, Jordan Schneider, Scott Niekum)
1J TimeSHAP: Explaining Recurrent Models through Sequence Perturbations (João Sousa, Pedro Saleiro, André F. Cruz, Mario A. T. Figueiredo, Pedro Bizarro)
1K Teaching the Machine to Explain Itself using Domain Knowledge (Vladimir Balayan, Pedro Saleiro, Catarina Belém, Ludwig Krippahl, Pedro Bizarro)

Session 2

2A On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks (Stephen Mussmann, Robin Jia, Percy Liang)
2B NetReAct: Interactive Learning for Network Summarization (Sorour E Amiri, Bijaya Adhikari, John Wenskovitch, Alexander Rodriguez, Michelle Dowling, Christopher North, B. Aditya Prakash)
2C The Design and Development of Games with a Purpose for AI Systems (Zahra Ashktorab, Casey Dugan, J. Johnson, Qian Pan, Wei Zhang)
2D What more can Entity Linking do for Question Answering? (Jordan Lee Boyd-Graber, Pedro Rodriguez, Naveen Janaki Raman)
2E Local vs. Global interpretations for NLP (Nimrah Shakeel)
2F Evidential Reasoning with Expert-Guided Machine Learning (Xueying Ding, Gopaljee Atulya, Aarti Singh, Alex Davis, Shane Fazzio)
2G On the Utility of Active Instance Selection for Few-Shot Learning (Pouya Pezeshkpour, Zhengli Zhao, Sameer Singh)
2H Human Adversarial QA: Did the Model Understand the Paragraph? (Prachi Shriram Rahurkar, Matthew Lyle Olson, Prasad Tadepalli)
2I Human-in-the-loop solution for scoring economic development from geospatial data (Sungwon Park, Donghyun Ahn, Sungwon Han, Eunji Lee, Danu Kim, Jeasurk Yang, Susang Lee, Sangyoon Park, Hyunjoo Yang, Jihee Kim, Meeyoung Cha)
2J Real-Time Visual Feedback for Educative Benchmark Creation: A Human-and-Metric-in-the-Loop Workflow (Anjana Arunkumar, Swaroop Mishra, Bhavdeep Singh Sachdeva, Chitta Baral, Chris Bryan)
2K ReGAL: Rule-Generative Active Learning for Model-in-the-Loop Weak Supervision (David Kartchner, Wendi Ren, Davi Nakajima An, Chao Zhang, Cassie Mitchell)