SCI-FII: Speculative conversational interface framework for incremental inference on modularized services

Jinho Lee; Inseok Hwang; Thomas Hubregtsen; Anne E. Gattiker; Christopher M. Durham

doi:10.1109/MDM.2017.45

SCI-FII: Speculative conversational interface framework for incremental inference on modularized services

Jinho Lee, Inseok Hwang, Thomas Hubregtsen, Anne E. Gattiker, Christopher M. Durham

College of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

We propose Sci-Fii, a speculative conversational interface framework for incremental inference on modularized services. To build one's own conversational interface with existing business logic, cloud-based modularized services offer a suite of ready-to-use components to ease development, ensure cross-platform flexibility, and encapsulate computational complexities. However developing with the modularized services often results in a chain of discrete modules with limited inter-module data sharing, which yields unnecessarily long response times of the conversational interface, aggravates user experiences, and eventually harms user retention. Sci-Fii offers a uniform framework that enables existing serviced modules to benefit from intermediate data and early parallel execution. Transparent to developers, Sci-Fii helps the end-to-end conversational interface system work fluidly and exhibit faster and more natural response times.

Original language	English
Title of host publication	Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	278-285
Number of pages	8
ISBN (Electronic)	9781538639320
DOIs	https://doi.org/10.1109/MDM.2017.45
Publication status	Published - 2017 Jun 29
Event	18th IEEE International Conference on Mobile Data Management, MDM 2017 - Daejeon, Korea, Republic of Duration: 2017 May 29 → 2017 Jun 1

Publication series

Name	Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017

Conference

Conference	18th IEEE International Conference on Mobile Data Management, MDM 2017
Country/Territory	Korea, Republic of
City	Daejeon
Period	17/5/29 → 17/6/1

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

All Science Journal Classification (ASJC) codes

Hardware and Architecture
Computer Networks and Communications
Information Systems and Management

Access to Document

10.1109/MDM.2017.45

Cite this

Lee, J., Hwang, I., Hubregtsen, T., Gattiker, A. E., & Durham, C. M. (2017). SCI-FII: Speculative conversational interface framework for incremental inference on modularized services. In Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017 (pp. 278-285). Article 7962463 (Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MDM.2017.45

Lee, Jinho ; Hwang, Inseok ; Hubregtsen, Thomas et al. / SCI-FII : Speculative conversational interface framework for incremental inference on modularized services. Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 278-285 (Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017).

@inproceedings{79f466a76999406d973af8e891a7523b,

title = "SCI-FII: Speculative conversational interface framework for incremental inference on modularized services",

abstract = "We propose Sci-Fii, a speculative conversational interface framework for incremental inference on modularized services. To build one's own conversational interface with existing business logic, cloud-based modularized services offer a suite of ready-to-use components to ease development, ensure cross-platform flexibility, and encapsulate computational complexities. However developing with the modularized services often results in a chain of discrete modules with limited inter-module data sharing, which yields unnecessarily long response times of the conversational interface, aggravates user experiences, and eventually harms user retention. Sci-Fii offers a uniform framework that enables existing serviced modules to benefit from intermediate data and early parallel execution. Transparent to developers, Sci-Fii helps the end-to-end conversational interface system work fluidly and exhibit faster and more natural response times.",

author = "Jinho Lee and Inseok Hwang and Thomas Hubregtsen and Gattiker, {Anne E.} and Durham, {Christopher M.}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 18th IEEE International Conference on Mobile Data Management, MDM 2017 ; Conference date: 29-05-2017 Through 01-06-2017",

year = "2017",

month = jun,

day = "29",

doi = "10.1109/MDM.2017.45",

language = "English",

series = "Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "278--285",

booktitle = "Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017",

address = "United States",

}

Lee, J, Hwang, I, Hubregtsen, T, Gattiker, AE & Durham, CM 2017, SCI-FII: Speculative conversational interface framework for incremental inference on modularized services. in Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017., 7962463, Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017, Institute of Electrical and Electronics Engineers Inc., pp. 278-285, 18th IEEE International Conference on Mobile Data Management, MDM 2017, Daejeon, Korea, Republic of, 17/5/29. https://doi.org/10.1109/MDM.2017.45

SCI-FII: Speculative conversational interface framework for incremental inference on modularized services. / Lee, Jinho; Hwang, Inseok; Hubregtsen, Thomas et al.
Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 278-285 7962463 (Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - SCI-FII

T2 - 18th IEEE International Conference on Mobile Data Management, MDM 2017

AU - Lee, Jinho

AU - Hwang, Inseok

AU - Hubregtsen, Thomas

AU - Gattiker, Anne E.

AU - Durham, Christopher M.

PY - 2017/6/29

Y1 - 2017/6/29

N2 - We propose Sci-Fii, a speculative conversational interface framework for incremental inference on modularized services. To build one's own conversational interface with existing business logic, cloud-based modularized services offer a suite of ready-to-use components to ease development, ensure cross-platform flexibility, and encapsulate computational complexities. However developing with the modularized services often results in a chain of discrete modules with limited inter-module data sharing, which yields unnecessarily long response times of the conversational interface, aggravates user experiences, and eventually harms user retention. Sci-Fii offers a uniform framework that enables existing serviced modules to benefit from intermediate data and early parallel execution. Transparent to developers, Sci-Fii helps the end-to-end conversational interface system work fluidly and exhibit faster and more natural response times.

AB - We propose Sci-Fii, a speculative conversational interface framework for incremental inference on modularized services. To build one's own conversational interface with existing business logic, cloud-based modularized services offer a suite of ready-to-use components to ease development, ensure cross-platform flexibility, and encapsulate computational complexities. However developing with the modularized services often results in a chain of discrete modules with limited inter-module data sharing, which yields unnecessarily long response times of the conversational interface, aggravates user experiences, and eventually harms user retention. Sci-Fii offers a uniform framework that enables existing serviced modules to benefit from intermediate data and early parallel execution. Transparent to developers, Sci-Fii helps the end-to-end conversational interface system work fluidly and exhibit faster and more natural response times.

UR - http://www.scopus.com/inward/record.url?scp=85026779448&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85026779448&partnerID=8YFLogxK

U2 - 10.1109/MDM.2017.45

DO - 10.1109/MDM.2017.45

M3 - Conference contribution

AN - SCOPUS:85026779448

T3 - Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017

SP - 278

EP - 285

BT - Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 29 May 2017 through 1 June 2017

ER -

Lee J, Hwang I, Hubregtsen T, Gattiker AE, Durham CM. SCI-FII: Speculative conversational interface framework for incremental inference on modularized services. In Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 278-285. 7962463. (Proceedings - 18th IEEE International Conference on Mobile Data Management, MDM 2017). doi: 10.1109/MDM.2017.45

SCI-FII: Speculative conversational interface framework for incremental inference on modularized services

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this