Details of work my colleagues, students and I have been involved with can be found on this page
Details of other work from the AI Institute on "Knowledge enhanced chatbots" in health can be found at page - kHealth Chatbots
O1. Multi-modal chatbots
O2. Combining deep-learning and symbolic (reasoning) methods for building dialog managers
O3. Generating chatbots from data
O4. Building trusted AI and Chatbots
O5. Studies on impact of AI and Chatbots on people
O6. Domain-specific chatbots - (a) Education: Helping a group of students to learn (“Future of Work”), (b) Home Improvement and networking: jointly with Tantiv4, (c) Health
Dialog Strategy/ Planning
Vishal Pallagani and Biplav Srivastava, A Generic Dialog Agent for Information Retrieval Based on Automated Planning Within a Reinforcement Learning Platform, Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL), International Conference on Automated Planning and Scheduling (ICAPS), 2021 [Planning/RL, Dialog]. Also see demo video.
Yunfeng Zhang, Vera Liao, Biplav Srivastava, Towards an optimal dialog strategy for information retrieval using both open-ended and close-ended questions, Proc. Intelligent User Interfaces (IUI 2018, Tokyo, Japan, March 2018 [Dialog Strategy].
Kartik Talamadupula, Biplav Srivastava, Jeffrey O. Kephart, Workflow Complexity for Collaborative Interactions: Where are the Metrics?- A Challenge, ICAPS 2017 Workshop on User Interfaces and Scheduling and Planning (UISP), June 2017. At: http://icaps17.icaps-conference.org/workshops/UISP/. On Arxiv at: https://arxiv.org/abs/1709.04524 [Plan Metrics, Collaboration]
Q Vera Liao, Biplav Srivastava, Pavan Kapanipathi, A Measure for Dialog Complexity and its Application in Streamlining Service Operations, On Arxiv at: https://arxiv.org/abs/1708.04134, 2017 [Dialog analysis]
Dialogs, Fairness and Application Readiness
Biplav Srivastava, Kausik Lakkaraju, Tarmo Koppel, Vignesh Narayanan, Ashish Kundu, Sachindra Joshi, Evaluating Chatbots to Promote Users' Trust -- Practices and Open Problems, On Arxiv at: https://arxiv.org/abs/2309.05680, 2023 [Chatbot evaluation, AI trust]
Biplav Srivastava, Did Chatbots Miss Their 'Apollo Moment'? A Survey of the Potential, Gaps and Lessons from Using Collaboration Assistants During COVID-19, Cell PATTERNS, Aug 2021. (Preprint on Arxiv: https://arxiv.org/abs/2103.05561, March 2021) [Chatbots, COVID]
Biplav Srivastava, Francesca Rossi, Sheema Usmani, and Mariana Bernagozzi, Personalized Chatbot Trustworthiness Ratings, IEEE Transactions on Technology and Society, 2020. Preprint on Arxiv: https://arxiv.org/abs/2005.10067, May 2020 [Chatbots, Ethics Rating]
Biplav Srivastava, On Chatbots Exhibiting Goal-Directed Autonomy in Dynamic Environments, AAAI Spring Symposium 2018 on Integrating Representation, Reasoning, Learning, and Execution for Goal Directed Autonomy, Palo Alto, CA, USA, March 26-28, 2018. [Chatbots, Decision Making]
Biplav Srivastava, Decision-support for the Masses by Enabling Conversations with Open Data, On Arxiv at: https://arxiv.org/abs/1809.06723, Sep 2018 [Chatbot, Open Data]
C1. Decision-support in education
Kausik Lakkaraju, Thahimum Hassan, Vedant Khandelwal, Prathamjeet Singh, Cassidy Bradley, Ronak Shah, Forest Agostinelli, Biplav Srivastava and Dezhi Wu, ALLURE: A Multi-modal Guided Environment for Helping Children Learn to Solve a Rubik's Cube with Automatic Solving and Interactive Explanations. Demo at AAAI 2022, Video on Youtube - https://www.youtube.com/watch?v=-0aKDVoEGvs (Sep 2021) [AI-Chatbots, Rubik's Cube, Education]
C2. Decision-support with water data
Jason Ellis, Biplav Srivastava, Rachel K. E. Bellamy, Andy Aaron, Water Advisor – A Data-Driven, Multi-Modal, Contextual Assistant to Help with Water Usage Decisions, at Proc. 32nd AAAI Conference on Artificial Intelligence (AAAI-18), New Orleans, Lousiana, USA, Feb 2-7, 2018. ". Video on Youtube - https://www.youtube.com/watch?v=z4x44sxC3zA (Sep 2017).
Blue Water - https://sites.google.com/site/biplavsrivastava/research-1/bluewater
C3. Decision-support with astronomy data for group of people
Jeffrey O. Kephart, Victor C. Dibia, Jason Ellis, Biplav Srivastava, Kartik Talamadupula, Mishal Dholakia, An Embodied Cognitive Assistant for Visualizing and Analyzing Exoplanet Data, IEEE Internet Computing Journal (Special Issue on Cognitive Services and Intelligent Chatbots), March 2019. [AI-Chatbots, Astronomy]
Jeffrey O. Kephart, Victor C. Dibia, Jason Ellis, Biplav Srivastava, Kartik Talamadupula, Mishal Dholakia, A Cognitive Assistant for Visualizing and Analyzing Exoplanets, at Proc. 32nd AAAI Conference on Artificial Intelligence (AAAI-18), New Orleans, Lousiana, USA, Feb 2-7, 2018. Awarded AAAI 2018 Best Demonstration Award. Video - https://www.youtube.com/watch?v=Fg_seQM9T0k (Feb 2018).
C4. Chatbot interface to Commercial Product in Talent Management, https://www.ibm.com/talent-management/career-coach [Commercial, Human Resources]
C5. Decision-support with a smart room and home environment
Tathagata Chakraborti, Kshitij P. Fadnis, Kartik Talamadupula, Mishal Dholakia, Biplav Srivastava, Jeffrey O. Kephart, Rachel K. E. Bellamy, Planning and visualization for a smart meeting room assistant1: A case study in the Cognitive Environments Laboratory at IBM T.J. Waston Research Center, Yorktown, AI Communications, 1-9, 2019 [Smart room, Planning, Visualization]
Tathagata Chakraborti, Kshitij P. Fadnis, Kartik Talamadupula, Mishal Dholakia, Biplav Srivastava, Jeffrey O. Kephart, Rachel K. E. Bellamy, Visualizations for an Explainable Planning Agent, Awarded Runner-up for ICAPS 2018 Best Demonstration. Video - https://youtu.be/ZEHxCKodEGs (June 2018). Demo paper: https://www.ijcai.org/proceedings/2018/0849.pdf]
Tathagata Chakraborti, Kartik Talamadupula, Mishal Dholakia, Biplav Srivastava, Jeffrey O. Kephart, Rachel K. E. Bellamy, Mr. Jones - Towards a Proactive Smart Room Orchestrator, AAAI 2017 Fall Symposium on Human-Agent Groups: Studies, Algorithms and Challenges, Washington, USA, Nov 2017. On Arxiv at: https://arxiv.org/abs/1709.04517, Sep 2017. [Plan Recognition, Collaboration]
Kausik Lakkaraju, Vinamra Palaiyya, Sai Teja Paladi, Chinmayi Appajigowda, Biplav Srivastava, Lokesh Johri, Data-based Insights for the Masses: Scaling Natural Language Querying to Middleware Data", DASFAA-2022, Video - https://vimeo.com/651270271 (April 2022) [IoT - power and router usage]
C6. Decision support with train travel
Ramashish Gaurav, Biplav Srivastava, Estimating Train Delays in a Large Rail Network Using a Zero Shot Markov Model, IEEE International Conference on Intelligent Transportation Systems (ITSC). On Arxiv at: https://arxiv.org/abs/1806.02825, June 2018 [Train delay, prediction]
Himadri Mishra, Ramashish Gaurav, Biplav Srivastava, Train Status Assistant for Indian Railways, On Arxiv at: https://arxiv.org/abs/1809.08509, Sep 2018, Video: https://www.youtube.com/watch?v=a-ABv29H6XU [Chatbot, Train delay assistant]
C7. Tackling Corruption With Agents
Biplav Srivastava, Tackling Corruption With Agents & ICT: A Vision, On Arxiv at: https://arxiv.org/abs/1701.06426 January 2017. [Corruption, Agents]
C8. Decision support in health
Surjodeep Sarkar, Manas Gaur, L Chen, Muskan Garg, Biplav Srivastava, Bhaktee Dongaonkar, Towards Explainable and Safe Conversational Agents for Mental Health: A Survey, https://arxiv.org/abs/2304.13191, April 2023 [Metal Heath, Chatbot Survey]
Pratyush Kumar Sahoo, Nidhi Malhotra, Shirley Sanjay Kokane, Biplav Srivastava, Harsh Narayan Tiwari and Sushant Sawant, Utilizing Predictive Analysis to Aid Emergency Medical Services, 5th International Workshop on Health Intelligence, (W3PHIAI-21), Feb 8-9, 2021, Poster.
World Economic Forum (WEF) created a framework on ethical chatbot building for health called Chatbot Reset by facilitating discussions by a variety of stakeholders around the globe on issues of relevance to developers, medical administrators and regulators, among others. Then, 4 different pilot projects used it to build and deploy chatbots including the Apollo group in India. A report has come out on how the 4 projects used it and what they found. I got a an opportunity to contribute to the Chatbot Reset framework.
P1. CASY Hybrid workshops at University of South Carolina
Hybrid Conference on Collaborative Assistants for Society (CASY 2), Biplav Srivastava. This is a free-to-attend, two part event to promote the ethical usage of digital assistants in society for daily life activities. Phase 1 is scheduled to happen on 15th October, 2021 and will feature invited demos, a panel discussion and launch of a competition. Phase 2 will be on 11th February, 2022, and will have invited technical talks as well as conclude the talks.
Hybrid Conference on Collaborative Assistants for Society (CASY 2020), Biplav Srivastava. The free-to-attend event attracted 150+ registrations. It was meant to promote the ethical usage of digital assistants in society for daily life activities, 16 October, 2020. Mostly virtual with limited physical presence at the University of South Carolina.
P2. DEEP-DIAL Workshops at AAAI Conferences
P1. Workshop on Reasoning and Learning in Human-Agent Dialogs (DEEP-DIAL), in conjunction with 35th Conference of Association for Advancement of Artificial Intelligence (AAAI-21), Sathyanarayanan N. Aakur (Sathya) , Ullas Nambiar, Imed Zitouni, Biplav Srivastava, Virtual, Feb 2021.
P2. Hybrid Conference on Collaborative Assistants for Society (CASY 2020), Biplav Srivastava. This is a free-to-attend event to promote the ethical usage of digital assistants in society for daily life activities, 16 October, 2020. Mostly virtual with limited physical presence at the University of South Carolina.
P3. Workshop on Reasoning and Learning in Human-Agent Dialogs (DEEP-DIAL 2020), in conjunction with 34th Conference of Association for Advancement of Artificial Intelligence (AAAI-20), Ullas Nambiar, Imed Zitouni, Kshitij Fadnis, Biplav Srivastava, New York, NY, USA, Feb 2020.
P4. Workshop on Reasoning and Learning in Human-Agent Dialogs (DEEP-DIAL 2019), in conjunction with 33rd Conference of Association for Advancement of Artificial Intelligence (AAAI-19), Biplav Srivastava, Susanne Biundo, Ullas Nambiar, Imed Zitouni, Honolulu, Hawaii, USA, Jan 2019.
P5. Workshop on Reasoning and Learning in Human-Agent Dialogs (DEEP-DIAL 2018), in conjunction with 32nd Conference of Association for Advancement of Artificial Intelligence (AAAI-18), Biplav Srivastava, Susanne Biundo, Ullas Nambiar, Imed Zitouni, New Orleans, USA, Feb 2018.
US 12,067,983 – Robust useful and general task-oriented virtual assistants [tags: chatbot monitoring, execution]
US 12,028,295 – Generating a chatbot utilizing a data source [tags: chatbot generation, data]
US 11,797,820 – Data augmented training of reinforcement learning software agent [tags: reinforcement learning, training]
US 11,748,419, US 11,138,272 – Generating and executing an optimal dialogue strategy [tags: dialog, policy]
US 11,620,486 – Estimating and visualizing collaboration to facilitate automated plan generation [tags: human-planning collaboration, visualization]
US 11,966,706, US 11,443,121, US 10,565,316, US 10,114,816 - Assessing complexity of dialogs to streamline handling of service requests [tags: dialog, complexity]
US 11,386,338 – Integrating multiple domain problem solving in a dialog system for a user [tags: dialog, domain integration]
US 11,386,159 – Using a dialog system for integrating multiple domain learning and problem solving [tags: dialog, learning]
US 11,295,230 – Learning personalized actionable domain models [tags: Learning, Action models]
US 11,100,407 –Building domain models from dialog interactions [tags: dialog, analysis]
US 10,839,010 –Compact visualization of query search results [tags: search visualization]
US 10,740,370, US 10,387,463 – Dialog agent for conducting task-oriented computer-based communications [tags: dialogs, deep learning]
US 10,699,200, US 10,699,199 – System and Method for Learning Actionable Domain Models of Plans from Online Data [tags: Learning, Action models]
US 10,425,315 - Interactive personal digital assistant device [tags: dialogs, multi-agent]
US 10,410,385 - Generating hypergraph representations of dialog [tags: dialogs, summary]
US 10,387,564 – Automatically assessing document quality for domain-specific documentation [tags: doc management, learning]