TY - GEN
T1 - Enhancing scientific collaboration through knowledge base population and linking for meetings
AU - Gao, Ning
AU - Dredze, Mark
AU - Oard, Douglas W.
N1 - Funding Information:
This work has been supported in part by NSF Grants 1065250 and 1618695 and by a Mellon Foundation Coherence at Scale Doctoral Fellowship. Opinions, findings, conclusions or recommendations are those of the authors and do not necessarily reflect the ivwes foSNF roethMelnloFundation.
Publisher Copyright:
© 2018 IEEE Computer Society. All rights reserved.
PY - 2018
Y1 - 2018
N2 - Recent research on scientific collaboration shows that distributed interdisciplinary collaborations report comparatively poor outcomes, and the inefficiency of the coordination mechanisms is partially responsible for the problems. To improve information sharing between past collaborators and future team members, or reuse of collaboration records from one project by future researchers, this paper describes systems that automatically construct a knowledge base of the meetings from the calendars of participants, and that then link reference to those meetings found in email messages to the corresponding meeting in the knowledge base. This is work in progress in which experiments with a publicly available corporate email collection with calendar entries show that the knowledge base population function achieves high precision (0.98, meaning that almost all knowledge base entities are actually meetings) and that the accuracy of the linking from email messages to knowledge base entries (0.90) is already quite good.
AB - Recent research on scientific collaboration shows that distributed interdisciplinary collaborations report comparatively poor outcomes, and the inefficiency of the coordination mechanisms is partially responsible for the problems. To improve information sharing between past collaborators and future team members, or reuse of collaboration records from one project by future researchers, this paper describes systems that automatically construct a knowledge base of the meetings from the calendars of participants, and that then link reference to those meetings found in email messages to the corresponding meeting in the knowledge base. This is work in progress in which experiments with a publicly available corporate email collection with calendar entries show that the knowledge base population function achieves high precision (0.98, meaning that almost all knowledge base entities are actually meetings) and that the accuracy of the linking from email messages to knowledge base entries (0.90) is already quite good.
UR - http://www.scopus.com/inward/record.url?scp=85108292301&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85108292301&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85108292301
T3 - Proceedings of the Annual Hawaii International Conference on System Sciences
SP - 597
EP - 606
BT - Proceedings of the 51st Annual Hawaii International Conference on System Sciences, HICSS 2018
A2 - Bui, Tung X.
PB - IEEE Computer Society
T2 - 51st Annual Hawaii International Conference on System Sciences, HICSS 2018
Y2 - 2 January 2018 through 6 January 2018
ER -