skip to main content


Title: Multi-Modal Repairs of Conversational Breakdowns in Task-Oriented Dialogs
A major problem in task-oriented conversational agents is the lack of support for the repair of conversational breakdowns. Prior studies have shown that current repair strategies for these kinds of errors are often ineffective due to: (1) the lack of transparency about the state of the system's understanding of the user's utterance; and (2) the system's limited capabilities to understand the user's verbal attempts to repair natural language understanding errors. This paper introduces SOVITE, a new multi-modal speech plus direct manipulation interface that helps users discover, identify the causes of, and recover from conversational breakdowns using the resources of existing mobile app GUIs for grounding. SOVITE displays the system's understanding of user intents using GUI screenshots, allows users to refer to third-party apps and their GUI screens in conversations as inputs for intent disambiguation, and enables users to repair breakdowns using direct manipulation on these screenshots. The results from a remote user study with 10 users using SOVITE in 7 scenarios suggested that SOVITE's approach is usable and effective.  more » « less
Award ID(s):
1814472
NSF-PAR ID:
10302227
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
ACM Symposium on User Interface Software and Technology
Page Range / eLocation ID:
1094 to 1107
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Many people with low vision rely on screen-magnifier assistive technology to interact with productivity applications such as word processors, spreadsheets, and presentation software. Despite the importance of these applications, little is known about their usability with respect to low-vision screen-magnifier users. To fill this knowledge gap, we conducted a usability study with 10 low-vision participants having different eye conditions. In this study, we observed that most usability issues were predominantly due to high spatial separation between main edit area and command ribbons on the screen, as well as the wide span grid-layout of command ribbons; these two GUI aspects did not gel with the screen-magnifier interface due to lack of instantaneous WYSIWYG (What You See Is What You Get) feedback after applying commands, given that the participants could only view a portion of the screen at any time. Informed by the study findings, we developed MagPro, an augmentation to productivity applications, which significantly improves usability by not only bringing application commands as close as possible to the user's current viewport focus, but also enabling easy and straightforward exploration of these commands using simple mouse actions. A user study with nine participants revealed that MagPro significantly reduced the time and workload to do routine command-access tasks, compared to using the state-of-the-art screen magnifier. 
    more » « less
  2. A search trail is an interactive visualization of how a previous searcher approached a related task. Using search trails to assist users requires understanding aspects of the task, user, and trails. In this paper, we examine two questions. First, what are task characteristics that influence a user's ability to gain benefits from others' trails? Second, what is the impact of a "mismatch" between a current user's task and previous user's task which originated the trail? We report on a study that investigated the influence of two factors on participants' perceptions and behaviors while using search trails to complete tasks. Our first factor, task scope, focused on the scope of the task assigned to the participant (broad to narrow). Our manipulation of this factor involved varying the number of constraints associated with tasks. Our second factor, trail scope, focused on the scope of the task that originated the search trails given to participants. We investigated how task scope and trail scope affected participants' (RQ1) pre-task perceptions, (RQ2) post-task perceptions, and (RQ3) search behaviors. We discuss implications of our results for systems that use search trails to provide assistance. 
    more » « less
  3. Insects maintain remarkable agility after incurring severe injuries or wounds. Although robots driven by rigid actuators have demonstrated agile locomotion and manipulation, most of them lack animal-like robustness against unexpected damage. Dielectric elastomer actuators (DEAs) are a class of muscle-like soft transducers that have enabled nimble aerial, terrestrial, and aquatic robotic locomotion comparable to that of rigid actuators. However, unlike muscles, DEAs suffer local dielectric breakdowns that often cause global device failure. These local defects severely limit DEA performance, lifetime, and size scalability. We developed DEAs that can endure more than 100 punctures while maintaining high bandwidth (>400 hertz) and power density (>700 watt per kilogram)—sufficient for supporting energetically expensive locomotion such as flight. We fabricated electroluminescent DEAs for visualizing electrode connectivity under actuator damage. When the DEA suffered severe dielectric breakdowns that caused device failure, we demonstrated a laser-assisted repair method for isolating the critical defects and recovering performance. These results culminate in an aerial robot that can endure critical actuator and wing damage while maintaining similar accuracy in hovering flight. Our work highlights that soft robotic systems can embody animal-like agility and resilience—a critical biomimetic capability for future robots to interact with challenging environments. 
    more » « less
  4. We investigate direct manipulation of graphical encodings as a method for interacting with visualizations. There is an increasing interest in developing visualization tools that enable users to perform operations by directly manipulating graphical encodings rather than external widgets such as checkboxes and sliders. Designers of such tools must decide which direct manipulation operations should be supported, and identify how each operation can be invoked. However, we lack empirical guidelines for how people convey their intended operations using direct manipulation of graphical encodings. We address this issue by conducting a qualitative study that examines how participants perform 15 operations using direct manipulation of standard graphical encodings. From this study, we 1) identify a list of strategies people employ to perform each operation, 2) observe commonalities in strategies across operations, and 3) derive implications to help designers leverage direct manipulation of graphical encoding as a method for user interaction. 
    more » « less
  5. This paper focuses on developing a security mechanism geared towards appified smart-home platforms. Such platforms often expose programming interfaces for developing automation apps that mechanize different tasks among smart sensors and actuators (e.g., automatically turning on the AC when the room temperature is above 80 F). Due to the lack of effective access control mechanisms, these automation apps can not only have unrestricted access to the user's sensitive information (e.g., the user is not at home) but also violate user expectations by performing undesired actions. As users often obtain these apps from unvetted sources, a malicious app can wreak havoc on a smart-home system by either violating the user's security and privacy, or creating safety hazards (e.g., turning on the oven when no one is at home). To mitigate such threats, we propose Expat which ensures that user expectations are never violated by the installed automation apps at runtime. To achieve this goal, Expat provides a platform-agnostic, formal specification language UEI for capturing user expectations of the installed automation apps' behavior. For effective authoring of these expectations (as policies) in UEI, Expat also allows a user to check the desired properties (e.g., consistency, entailment) of them; which due to their formal semantics can be easily discharged by an SMT solver. Expat then enforces UEI policies in situ with an inline reference monitor which can be realized using the same app programming interface exposed by the underlying platform. We instantiate Expat for one of the representative platforms, OpenHAB, and demonstrate it can effectively mitigate a wide array of threats by enforcing user expectations while incurring only modest performance overhead. 
    more » « less