The AAAI-20 Workshop on Intelligent Process Automation

Hilton New York Midtown, New York, NY, USA

February 7th 2020

TL;DR: A one-day AAAI-20 workshop focusing on learning structured & executable processes (programs) from human demonstrations, natural language specifications, or interactions with an environment. Submissions of previously unpublished or recently published papers welcome. $1000 Best Paper Award. Free lunch for authors. Non-archival proceedings.

How to free people from the mundane and repetitive parts of their daily workload? Robotic Process Automation (RPA) addresses this problem by developing software agents (robots) that can mimic human users to perform a variety of business tasks on their computers (e.g., processing the invoices received from emails). Since the term RPA was coined by Blue Prism in 2012, it has spread through enterprises in many different industrial sections (finance, health, telecommunication, manufacturing, and so on). It is estimated that the RPA software market will reach $3.97 billion by 2025.

Current RPA systems are mostly rule-based. Artificial Intelligence (AI) promises to take RPA to new heights, but so far the AI research efforts related to the different aspects of RPA have been largely isolated. This AAAI-20 workshop aims to bridge the gap between the rapidly growing RPA software industry and the AI research community. It will bring together researchers from different fields to exchange ideas and foster discussions on this important, novel application domain for AI.

Workshop Topics

Technical topics include, but are not limited to:

  • demo2process (learning a task-completion software agent from human demonstrations or behavior logs): interactive task learning, imitation learning, program induction, programming by example, process mining, ...

  • text2process (learning a task-completion software agent from step-by-step natural language text descriptions of the process): learning by instruction, conversational machine learning, natural language programming, natural language grounding, ...

  • task2process (learning a task-completion software agent directly from the task as defined by an environment with its reward function or some input/output examples): reinforcement learning, neural program synthesis, Bayesian program learning, ...

The common theme is that the learning system’s output would not be simply class labels or numerical predictions, but structured & executable processes (in the form of state-action policies, if-this-then-that rules, finite-state automatons, or programs in domain-specific languages), which makes it more challenging than most of today’s machine learning research problems. In addition, such automated processes must be safe, robust and explainable to be ready for enterprise-level applications, which also poses new research challenges.

Furthermore, this workshop strongly encourages interdisciplinary submissions from psychologists, economists, or social scientists on the following topics.

  • human-in-the-loop: the interaction between human users and software robots in attended automation.

  • human-outside-the-loop: the social and organizational impacts of software robots taking over some workloads or responsibilities from human users.

Paper Submission

We welcome contributions of two types.

  • New, previously unpublished papers which could be either long (6-8 pages) or short (2-4 pages). Such submissions will be given priority.

  • Preprints (the accepted version, not the final published version) of recently published or in-press papers (no page limit). Such submissions must indicate clearly when and where the corresponding papers have been or will be published.

All submissions should be formatted in the AAAI-20 style and will be peer-reviewed by multiple reviewers. The authors' identities must be concealed to enable double-blind peer-review, and all the conflicts of interests must be declared in advance. The accepted papers will be published on arXiv.org and they will be included in a non-archival workshop proceedings (which does not prevent the authors from submitting them to other venues in the future). Blue Prism will sponsor a Best Paper Award of $1000. It will be selected from the accepted papers by a committee consisting of both academic and industrial experts.


Important Dates

[AoE time (UTC-12)]

  • November 8th 2019 EXTENDED to November 15th 2019: Abstract submission due

  • November 15th 2019: Full paper submission due (HARD DEADLINE, no extension)

  • December 4th 2019 EXTENDED to December 6th 2019: Notification of acceptance/rejection

  • December 13th 2019: AAAI-20 early registration deadline

  • January 7th 2020: Camera-ready version due

  • January 10th 2020: AAAI-20 late registration deadline

  • February 7th 2020: Workshop at AAAI-20

Workshop Programme

Friday, February 7th 2020. [@ Concourse C on the Concourse floor]

  • 07:30am-08:30am AAAI-20 Badge Pickup and Onsite Registration [@ 2nd Floor Promenade]

  • 08:30am-09:30am Keynote Speech by Sumit Gulwani (Microsoft Research) [Chair: Jacques Cali]

  • 09:30am-10:30am Oral Presentations (x3) [Chair: Murat Sensoy]

      • #27. D Ferreira, J Rozanova, K Dubba, D Zhang and A Freitas. On the Evaluation of Intelligence Process Automation. arXiv:2001.02639

      • #09. S Agostinelli, A Marrella and M Mecella. Towards Intelligent Robotic Process Automation for BPMers. arXiv:2001.00804

      • #08. X Han, Y Dang, L Mei, S Li, L Hu, S Agarwal and X Zhou. Automatic Business Process Structure Discovery using Ordered Neurons LSTM: A Preliminary Study. arXiv:2001.01243

  • 10:30am-11:00am Coffee Break

  • 11:00am-12:00pm Poster Presentations (x5)

      • #04. C Kumar, N Gantayat, S Dechu and T Horváth. Online Similarity Learning with Feedback for Invoice Line Item Matching. arXiv:2001.00288

      • #12. P Jenkins, H Wei, S Jenkins and Z Li. A Probabilistic Simulator of Spatial Demand for Product Allocation. arXiv:2001.03210

      • #20. K Pugdeethosapol, A Shrestha, H Fang and Q Qiu. High-Level Plan for Behavioral Robot Navigation with Natural Language Directions and R-NET. arXiv:2001.02330

      • #03. A Ayub and A Wagner. A Robot that Learns Connect Four Using Game Theory and Demonstrations. arXiv:2001.01004

      • #14. Y Chen and E Wu. Monte Carlo Tree Search for Generating Interactive Data Analysis Interfaces. arXiv:2001.01902

  • 12:00pm-01:30pm Free Lunch for Authors [@ Ted's Montana Grill]

  • 01:30pm-02:30pm Keynote Speech by Joyce Chai (University of Michigan) [Chair: Dell Zhang]

  • 02:30pm-03:30pm Oral Presentations (x3) [Chair: John Reid]

      • #16. Y Rizk, A Bhandwalder, S Boag, T Chakraborti, V Isahagian, Y Khazaeni, F Pollock and M Unuvar. A Unified Conversational Assistant Framework for Business Process Automation. arXiv:2001.03543

      • #15. N Ito, A Aizawa and Y Suzuki. From Natural Language Instructions to Complex Processes: Issues on Chaining Trigger Action Rules. arXiv:2001.02462

      • #29. T Chakraborti and Y Khazaeni. D3BA: A Tool for Optimizing Business Processes Using Non-Deterministic Planning. arXiv:2001.02619

  • 03:30pm-04:00pm Coffee Break

  • 04:00pm-04:45pm Invited Talk by Toby Jia-Jun Li (Carnegie Mellon University) [Chair: Julian Richardson]

      • #07. T Li, M Radensky, J Jia, K Singarajah, TM Mitchell and BA Myers. Interactive Task and Concept Learning from Natural Language Instructions and GUI Demonstrations. arXiv:1909.00031 [slides]

  • 04:45pm-05:25pm Oral Presentation of Best Paper Candidates (x2) [Chair: Jacques Cali]

      • #11. V Leno, A Polyvyanyy, M La Rosa, M Dumas and F Maggi. Automated Discovery of Data Transformations for Robotic Process Automation. arXiv:2001.01007 (*Best Paper Award Winner)

      • #35. A Moiseeva, D Trautmann and H Schütze. Multipurpose Intelligent Process Automation via Conversational Assistant. arXiv:2001.02284 (*Best Paper Award Runner-up)

  • 05:25pm-05:30pm Conclusion

Online Proceedings: arXiv:2001.05214

Programme Committee

  • Amos Azaria (Ariel University, Israel)

  • Dan Calian (Google Deepmind, UK)

  • Sarah Chasins (UC Berkeley, USA)

  • Xinyun Chen (UC Berkeley, USA)

  • Taolue Chen (Birkbeck, University of London, UK)

  • Weiwei Cheng (Blue Prism AI Labs, UK)

  • Chiara Di-Francescomarino (Fondazione Bruno Kessler, Italy)

  • Krishna Dubba (Blue Prism AI Labs, UK)

  • César Ferri (Universitat Politènica de València, Spain)

  • Francesco Folino (ICAR-C.N.R., Italy)

  • Po-Sen Huang (Google Deepmind, UK)

  • Thanapong Intharah (Khon Kaen University, Thailand)

  • James Kirk (University of Michigan, USA)

  • Toby Jia-Jun Li (Carnegie Mellon University, USA)

  • Xuelong Li (Chinese Academy of Sciences, China)

  • Chen Liang (Google Brain, USA)

  • Xixi Lu (Utrecht University, Netherlands)

  • Fabrizio Maggi (University of Tartu, Estonia)

  • Andrea Marrella (Sapienza Università di Roma, Italy)

  • Marco Montali (Free University of Bozen-Bolzano, Italy)

  • Luigi Pontieri (ICAR, C.N.R., Italy)

  • John Reid (Blue Prism AI Labs, UK)

  • Julian Richardson (Blue Prism AI Labs, UK)

  • Arik Senderovich (University of Toronto, Canada)

  • Murat Sensoy (Blue Prism AI Labs, UK)

  • Cyrus Shaoul (Leela AI, USA)

  • Richard Shin (UC Berkeley, USA)

  • Biplav Srivastava (IBM Research, USA)

  • Heiner Stuckenschmidt (University of Mannheim, Germany)

  • Emilio Sulis (University of Torino, Italy)

  • Sebastiaan van Zelst (Fraunhofer FIT & RWTH Aachen University, Germany)

  • Chenglong Wang (University of Washington, USA)

  • Matthias Weidlich (Humboldt-Universität zu Berlin, Germany)

  • Leslie Willcocks (London School of Economics and Political Science, UK)

Best Paper Committee

  • Jacques Cali (Blue Prism AI Labs, UK)

  • Joyce Chai (University of Michigan, USA)

  • Sumit Gulwani (Microsoft Research, USA)

  • Xuelong Li (Chinese Academy of Sciences, China)

  • Dawn Song (UC Berkeley, USA)

  • Dacheng Tao (University of Sydney, Australia)

  • Jun Wang (University College London, UK)

  • Emine Yilmaz (University College London, UK)

Organization Committee