An official website of the United States government
For the past 15 years, in computer-supported collaborative learning applications, conversational agents have been used to structure group interactions in online chat-based environments. A series of experimental studies has provided an empirical foundation for the design of chat based conversational agents that significantly improve learning over no-support control conditions and static-support control conditions. In this demo, we expand upon this foundation, bringing conversational agents to structure group interaction into physical spaces, with the specific goal of facilitating collaboration and learning in workplace scenarios.
more »
« less
Conversational Information Seeking
Conversational information seeking (CIS) is concerned with a sequence of interactions between one or more users and an information system. Interactions in CIS are primarily based on natural language dialogue, while they may include other types of interactions, such as click, touch, and body gestures. This monograph provides a thorough overview of CIS definitions, applications, interactions, interfaces, design, implementation, and evaluation. This monograph views CIS applications as including conversational search, conversational question answering, and conversational recommendation. Our aim is to provide an overview of past research related to CIS, introduce the current state-of-the-art in CIS, highlight the challenges still being faced in the community, and suggest future directions.
more »
« less
- Award ID(s):
- 2143434
- PAR ID:
- 10495320
- Publisher / Repository:
- now publishers
- Date Published:
- Journal Name:
- Foundations and Trends® in Information Retrieval
- Volume:
- 17
- Issue:
- 3-4
- ISSN:
- 1554-0669
- Page Range / eLocation ID:
- 244 to 456
- Subject(s) / Keyword(s):
- Applications of IR Usability, interactivity, and visualization issues in IR Architectures for IR IR on mobile platforms Natural language processing for IR Question answering Collaborative filtering and recommender systems
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Older adults often rely on information provided during doctors’ visits or online to manage their health but can experience challenges accessing this information at home. Recently, conversational assistants are being explored to aid navigation of health information included in online portals, but we still know little about users’ perceptions of using these tools for managing personal health information. In this paper, we conducted a wizard-of-oz study to better understand older adults’ perceptions of a conversational assistant, MIHA, to help with navigating personal health information. Participants saw value in using a tool such as MIHA to help facilitate access to their personal health information and to help them become more engaged in their health. Participants believed MIHA’s features helped build confidence in the responses returned, but made suggestions for improving the interactions. We share insights of potential uses and design implications for conversational assistants that help older adults navigate personal health information.more » « less
-
The overall goal of photonics research is to understand and control light in new and richer ways to facilitate new and richer applications. Many major developments to this end have relied on nonlinear optical techniques, such as lasing, mode-locking, and parametric downconversion, to enable applications based on the interactions of coherent light with matter. These processes often involve nonlinear interactions between photonic and material degrees of freedom spanning multiple spatiotemporal scales. While great progress has been made with relatively simple optimizations, such as maximizing single-mode coherence or peak intensity alone, the ultimate achievement of coherent light engineering is complete, multidimensional control of light–light and light–matter interactions through tailored construction of complex optical fields and systems that exploit all of light’s degrees of freedom. This capability is now within sight, due to advances in telecommunications, computing, algorithms, and modeling. Control of highly multimode optical fields and processes also facilitates quantitative and qualitative advances in optical imaging, sensing, communication, and information processing since these applications directly depend on our ability to detect, encode, and manipulate information in as many optical degrees of freedom as possible. Today, these applications are increasingly being enhanced or enabled by both multimode engineering and nonlinearity. Here, we provide a brief overview of multimode nonlinear photonics, focusing primarily on spatiotemporal nonlinear wave propagation and, in particular, on promising future directions and routes to applications. We conclude with an overview of emerging processes and methodologies that will enable complex, coherent nonlinear photonic devices with many degrees of freedom.more » « less
-
The ability to assess conversational interactions creates a challenge in assessing speaker turns over time, including frequency of occurrence, duration of each turn, and connecting speakers in a multispeaker context. This is of particular interest in the analysis of teacher-student or adult-child interactions in learning spaces. The creation of a visualization mechanism capable of providing a high-level representation of the overall conversational interactions without overburdening educators in reviewing student/child learning engagement would be of great significance. Chord diagrams can visualize such complex and disparate information in compact form. In this study, we explore the creation of ‘Chord Diagrams’ as a way to analyze talk time between a child and adult speakers in learning spaces. The proposed illustration provides an opportunity to study the variations in speech duration and the interaction among speakers that are involved in the communication with each other over a certain time learning duration.more » « less
-
Understanding and characterizing how people interact in information-seeking conversations will be a crucial component in developing effective conversational search systems. In this paper, we introduce a new dataset designed for this purpose and use it to analyze information-seeking conversations by user intent distribution, co-occurrence, and flow patterns. The MSDialog dataset is a labeled conversation dataset of question answering (QA) interactions between information seekers and providers from an online forum on Microsoft products. The dataset contains more than 2,000 multi-turn QA dialogs with 10,000 utterances that are annotated with user intents on the utterance level. Annotations were done using crowdsourcing. With MSDialog, we find some highly recurring patterns in user intent during an information-seeking process. They could be useful for designing conversational search systems. We will make our dataset freely available to encourage exploration of information-seeking conversation models.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1561/1500000081
