Using explicit semantic models to track situations across news articles

Earl J. Wagner*, Liu Jiahui, Lawrence A Birnbaum, Kenneth D Forbus, James Baker

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Online news is a rich information resource for learning about new, ongoing, and past events. Intelligence analysts, news junkies, and ordinary people all track developments in ongoing situations as they unfold over time and initiate queries to learn more about the past context of the events of interest to them. Brussell/STT (Situation Tracking Testbed) is an intelligent information system aimed at supporting this activity. Brussell employs a combination of explicit semantic models, information retrieval (IR), and information extraction (IE) in order to track a situation. It finds relevant news stories, organizes those stories around the aspects of the situation to which they pertain, and extracts certain basic facts about the situation for explicit representation. Brussell uses scripts as situation models for the episodes it tracks. Script instances are represented in CycL and stored in the Cyc knowledge-base. Models of ongoing situations can be reloaded and updated with new information as desired.

Original languageEnglish (US)
Title of host publicationEvent Extraction and Synthesis - Papers from the AAAI Workshop, Technical Report
Pages42-47
Number of pages6
VolumeWS-06-07
StatePublished - Dec 1 2006
Event2006 AAAI Workshop - Boston, MA, United States
Duration: Jul 16 2006Jul 20 2006

Other

Other2006 AAAI Workshop
CountryUnited States
CityBoston, MA
Period7/16/067/20/06

Fingerprint

Semantics
Testbeds
Information retrieval
Information systems

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Wagner, E. J., Jiahui, L., Birnbaum, L. A., Forbus, K. D., & Baker, J. (2006). Using explicit semantic models to track situations across news articles. In Event Extraction and Synthesis - Papers from the AAAI Workshop, Technical Report (Vol. WS-06-07, pp. 42-47)
Wagner, Earl J. ; Jiahui, Liu ; Birnbaum, Lawrence A ; Forbus, Kenneth D ; Baker, James. / Using explicit semantic models to track situations across news articles. Event Extraction and Synthesis - Papers from the AAAI Workshop, Technical Report. Vol. WS-06-07 2006. pp. 42-47
@inproceedings{48c705eac3084c3e8c9d39ee7bb1f2d6,
title = "Using explicit semantic models to track situations across news articles",
abstract = "Online news is a rich information resource for learning about new, ongoing, and past events. Intelligence analysts, news junkies, and ordinary people all track developments in ongoing situations as they unfold over time and initiate queries to learn more about the past context of the events of interest to them. Brussell/STT (Situation Tracking Testbed) is an intelligent information system aimed at supporting this activity. Brussell employs a combination of explicit semantic models, information retrieval (IR), and information extraction (IE) in order to track a situation. It finds relevant news stories, organizes those stories around the aspects of the situation to which they pertain, and extracts certain basic facts about the situation for explicit representation. Brussell uses scripts as situation models for the episodes it tracks. Script instances are represented in CycL and stored in the Cyc knowledge-base. Models of ongoing situations can be reloaded and updated with new information as desired.",
author = "Wagner, {Earl J.} and Liu Jiahui and Birnbaum, {Lawrence A} and Forbus, {Kenneth D} and James Baker",
year = "2006",
month = "12",
day = "1",
language = "English (US)",
isbn = "1577352890",
volume = "WS-06-07",
pages = "42--47",
booktitle = "Event Extraction and Synthesis - Papers from the AAAI Workshop, Technical Report",

}

Wagner, EJ, Jiahui, L, Birnbaum, LA, Forbus, KD & Baker, J 2006, Using explicit semantic models to track situations across news articles. in Event Extraction and Synthesis - Papers from the AAAI Workshop, Technical Report. vol. WS-06-07, pp. 42-47, 2006 AAAI Workshop, Boston, MA, United States, 7/16/06.

Using explicit semantic models to track situations across news articles. / Wagner, Earl J.; Jiahui, Liu; Birnbaum, Lawrence A; Forbus, Kenneth D; Baker, James.

Event Extraction and Synthesis - Papers from the AAAI Workshop, Technical Report. Vol. WS-06-07 2006. p. 42-47.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Using explicit semantic models to track situations across news articles

AU - Wagner, Earl J.

AU - Jiahui, Liu

AU - Birnbaum, Lawrence A

AU - Forbus, Kenneth D

AU - Baker, James

PY - 2006/12/1

Y1 - 2006/12/1

N2 - Online news is a rich information resource for learning about new, ongoing, and past events. Intelligence analysts, news junkies, and ordinary people all track developments in ongoing situations as they unfold over time and initiate queries to learn more about the past context of the events of interest to them. Brussell/STT (Situation Tracking Testbed) is an intelligent information system aimed at supporting this activity. Brussell employs a combination of explicit semantic models, information retrieval (IR), and information extraction (IE) in order to track a situation. It finds relevant news stories, organizes those stories around the aspects of the situation to which they pertain, and extracts certain basic facts about the situation for explicit representation. Brussell uses scripts as situation models for the episodes it tracks. Script instances are represented in CycL and stored in the Cyc knowledge-base. Models of ongoing situations can be reloaded and updated with new information as desired.

AB - Online news is a rich information resource for learning about new, ongoing, and past events. Intelligence analysts, news junkies, and ordinary people all track developments in ongoing situations as they unfold over time and initiate queries to learn more about the past context of the events of interest to them. Brussell/STT (Situation Tracking Testbed) is an intelligent information system aimed at supporting this activity. Brussell employs a combination of explicit semantic models, information retrieval (IR), and information extraction (IE) in order to track a situation. It finds relevant news stories, organizes those stories around the aspects of the situation to which they pertain, and extracts certain basic facts about the situation for explicit representation. Brussell uses scripts as situation models for the episodes it tracks. Script instances are represented in CycL and stored in the Cyc knowledge-base. Models of ongoing situations can be reloaded and updated with new information as desired.

UR - http://www.scopus.com/inward/record.url?scp=33846024091&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846024091&partnerID=8YFLogxK

M3 - Conference contribution

SN - 1577352890

SN - 9781577352891

VL - WS-06-07

SP - 42

EP - 47

BT - Event Extraction and Synthesis - Papers from the AAAI Workshop, Technical Report

ER -

Wagner EJ, Jiahui L, Birnbaum LA, Forbus KD, Baker J. Using explicit semantic models to track situations across news articles. In Event Extraction and Synthesis - Papers from the AAAI Workshop, Technical Report. Vol. WS-06-07. 2006. p. 42-47