Iris

Fast, Ethan; Chen, Binbin; Mendelsohn, Julia; Bassen, Jonathan; Bernstein, Michael S.

doi:10.1145/3173574.3174047

Cited by 73 publications

(10 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Technologists have developed question-answering systems to meet users' information needs in various domains including sports [72], work settings [44], and data science [20]. These systems exhibit a wide variety of designs.…”

Section: Question-answering Systems and User Perceptionmentioning

confidence: 99%

Causal Perception in Question-Answering Systems

Law

Endert

et al. 2021

Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Root cause analysis is a common data analysis task. While questionanswering systems enable people to easily articulate a why question (e.g., why students in Massachusetts have high ACT Math scores on average) and obtain an answer, these systems often produce questionable causal claims. To investigate how such claims might mislead users, we conducted two crowdsourced experiments to study the impact of showing different information on user perceptions of a question-answering system. We found that in a system that occasionally provided unreasonable responses, showing a scatterplot increased the plausibility of unreasonable causal claims. Also, simply warning participants that correlation is not causation seemed to lead participants to accept reasonable causal claims more cautiously. We observed a strong tendency among participants to associate correlation with causation. Yet, the warning appeared to reduce the tendency. Grounded in the findings, we propose ways to reduce the illusion of causality when using question-answering systems.

show abstract

Section: Question-answering Systems and User Perceptionmentioning

confidence: 99%

Causal Perception in Question-Answering Systems

Law

Endert

et al. 2021

Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…Another approach for handling ambiguities and vagueness in natural language inputs is to seek user clarification through conversations. For example, Iris [11] asks follow-up questions and presents possible options through conversations when the initial user input is incomplete or unclear. This approach lowers the learning barrier for end users, as it does not require them to clearly define everything up front.…”

Section: Natural Language Programmingmentioning

confidence: 99%

“…All conversational instructable agents need to map the user's inputs onto existing concepts, procedures and system functionalities supported by the agent, and to have natural language understanding mechanisms and training data in each task domain. Because of this constraint, existing agents limit their supported tasks to one or a few pre-defined domains, such as data science [11], email processing [3,46], or database queries [17].…”

Section: Natural Language Programmingmentioning

confidence: 99%

“…Other natural language programming approaches (e.g., [3,11,17,46]) restricted the problem space to specific task domains, so that they could constrain the space and the complexity of target program statements in order to enable the understanding of flexible user utterances. Such restrictions are due to the limited capabilities of existing natural language understanding techniques -they do not yet support robust understanding of utterances across diverse domains without extensive training data and structured prior knowledge within each domain.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

PUMICE: A Multi-Modal Agent that Learns Concepts and Conditionals from Natural Language and Demonstrations

Radensky

Jia

et al. 2019

Proceedings of the 32nd Annual ACM Symposium on User Interface Software and Technology

105

View full text Add to dashboard Cite

Figure 1. Example structure of how PUMICE learns the concepts and procedures in the command "If it's hot, order a cup of Iced Cappuccino." The numbers indicate the order of utterances. The screenshot on the right shows the conversational interface of PUMICE. In this interactive parsing process, the agent learns how to query the current temperature, how to order any kind of drink from Starbucks, and the generalized concept of "hot" as "a temperature (of something) is greater than another temperature". ABSTRACTNatural language programming is a promising approach to enable end users to instruct new tasks for intelligent agents. However, our formative study found that end users would often use unclear, ambiguous or vague concepts when naturally instructing tasks in natural language, especially when specifying conditionals. Existing systems have limited support for letting the user teach agents new concepts or explaining unclear concepts. In this paper, we describe a new multimodal domain-independent approach that combines natural language programming and programming-by-demonstration to allow users to first naturally describe tasks and associated conditions at a high level, and then collaborate with the agent to recursively resolve any ambiguities or vagueness through conversations and demonstrations. Users can also define new procedures and concepts by demonstrating and referring to contents within GUIs of existing mobile apps. We demonstrate this approach in PUMICE, an end-user programmable agent that implements this approach. A lab study with 10 users showed its usability.

show abstract

“…Based on user's intent, Vidura generates distinct responses from the various recommender modules to help users to accomplish research and educational tasks. The Vidura chatbot design is motivated by recent works on distributed cyberrobots for scientific workflows such as AVA 13 and IRIS, 14 and leverages Google's Dialogflow natural language processing framework 15 to enhance conversational understanding and interaction with users.…”

Section: Introductionmentioning

confidence: 99%

Recommender‐as‐a‐service with chatbot guided domain‐science knowledge discovery in a science gateway

Vekaria

Calyam

Sivarathri

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Scientists in disciplines such as neuroscience and bioinformatics are increasingly relying on science gateways for experimentation on voluminous data, as well as analysis and visualization in multiple perspectives. Though current science gateways provide easy access to computing resources, data sets and tools specific to the disciplines, scientists often use slow and tedious manual efforts to perform knowledge discovery to accomplish their research/education tasks. Recommender systems can provide expert guidance and can help them to navigate and discover relevant publications, tools, data sets, or even automate cloud resource configurations suitable for a given scientific task.To realize the potential of integration of recommenders in science gateways in order to spur research productivity, we present a novel "OnTimeRecommend" recommender system. The OnTimeRecommend comprises of several integrated recommender modules implemented as microservices that can be augmented to a science gateway in the form of a recommender-as-a-service. The guidance for use of the recommender modules in a science gateway is aided by a chatbot plug-in viz., Vidura Advisor. To validate our OnTimeRecommend, we integrate and show benefits for both novice and expert users in domain-specific knowledge discovery within two exemplar science gateways, one in neuroscience (CyNeuro) and the other in bioinformatics (KBCommons). K E Y W O R D Schatbot-guided user interface, knowledge discovery, microservices, recommender system, science gateway INTRODUCTIONRecent science and engineering research tasks are increasingly becoming data-intensive and thus relying on workflows to automate integration and analysis of voluminous data to test hypotheses. For example, research and training in neural science and engineering increasingly deal with diverse and voluminous multiparameter data, 1 posing unique challenges outlined in an NSF iNeuro report 2 as limited access to: multisomics data archives, 3 heterogeneous software 4 and computing resources (Neuroscience Gateway, 5 Amazon Web Services [AWS]), and multisite interdisciplinary expertise (e.g., engineering, biology and psychology). Existing distributed high-performance computing resources (HPC) and other cyberinfrastructure (CI) tools for data management support the related data analysis and visualization capabilities. However, to fully utilize such capabilities, neuroscientists (often with limited CI skills) are required to take valuable time away from the focus of knowledge discovery in neuroscience, in order to learn about how to use the various technologies.

show abstract

Iris

Cited by 73 publications

References 35 publications

Causal Perception in Question-Answering Systems

Causal Perception in Question-Answering Systems

PUMICE: A Multi-Modal Agent that Learns Concepts and Conditionals from Natural Language and Demonstrations

Recommender‐as‐a‐service with chatbot guided domain‐science knowledge discovery in a science gateway

Contact Info

Product

Resources

About