Finding new information via robust entity detection

Francisco Iacobelli*, Nathan Nichols, Lawrence A Birnbaum, Kristian J Hammond

*Corresponding author for this work

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

5 Citations (Scopus)

Abstract

Journalists and editors work under pressure to collect relevant details and background information about specific events. They spend a significant amount of time sifting through documents and finding new information such as facts, opinions or stakeholders (i.e. people, places and organizations that have a stake in the news). Spotting them is a tedious and cognitively intense process. One task, essential to this process, is to find and keep track of stakeholders. This task is taxing cognitively and in terms of memory. Tell Me More offers an automatic aid to this task. Tell Me More is a system that, given a seed story, mines the web for similar stories reported by different sources and selects only those stories which offer new information with respect to that original seed story. Much like a journalist, the task of detecting named entities is central to its success. In this paper we briefly describe Tell Me More and, in particular, we focus on Tell Me More's entity detection component. We describe an approach that combines off-the-shelf named entity recognizers (NERs) with WPED, an in-house publicly available NER that uses Wikipedia as its knowledge base. We show significant increase in precision scores with respect to traditional NERs. Lastly, we present an overall evaluation of Tell Me More using this approach.

Original languageEnglish (US)
Title of host publicationProactive Assistant Agents - Papers from the AAAI Fall Symposium, Technical Report
Pages32-37
Number of pages6
VolumeFS-10-07
StatePublished - Dec 1 2010
Event2010 AAAI Fall Symposium - Arlington, VA, United States
Duration: Nov 11 2010Nov 13 2010

Other

Other2010 AAAI Fall Symposium
CountryUnited States
CityArlington, VA
Period11/11/1011/13/10

Fingerprint

Seed
Data storage equipment

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Iacobelli, F., Nichols, N., Birnbaum, L. A., & Hammond, K. J. (2010). Finding new information via robust entity detection. In Proactive Assistant Agents - Papers from the AAAI Fall Symposium, Technical Report (Vol. FS-10-07, pp. 32-37)
Iacobelli, Francisco ; Nichols, Nathan ; Birnbaum, Lawrence A ; Hammond, Kristian J. / Finding new information via robust entity detection. Proactive Assistant Agents - Papers from the AAAI Fall Symposium, Technical Report. Vol. FS-10-07 2010. pp. 32-37
@inproceedings{515c804c405047ca895f9df853f78ff7,
title = "Finding new information via robust entity detection",
abstract = "Journalists and editors work under pressure to collect relevant details and background information about specific events. They spend a significant amount of time sifting through documents and finding new information such as facts, opinions or stakeholders (i.e. people, places and organizations that have a stake in the news). Spotting them is a tedious and cognitively intense process. One task, essential to this process, is to find and keep track of stakeholders. This task is taxing cognitively and in terms of memory. Tell Me More offers an automatic aid to this task. Tell Me More is a system that, given a seed story, mines the web for similar stories reported by different sources and selects only those stories which offer new information with respect to that original seed story. Much like a journalist, the task of detecting named entities is central to its success. In this paper we briefly describe Tell Me More and, in particular, we focus on Tell Me More's entity detection component. We describe an approach that combines off-the-shelf named entity recognizers (NERs) with WPED, an in-house publicly available NER that uses Wikipedia as its knowledge base. We show significant increase in precision scores with respect to traditional NERs. Lastly, we present an overall evaluation of Tell Me More using this approach.",
author = "Francisco Iacobelli and Nathan Nichols and Birnbaum, {Lawrence A} and Hammond, {Kristian J}",
year = "2010",
month = "12",
day = "1",
language = "English (US)",
isbn = "9781577354895",
volume = "FS-10-07",
pages = "32--37",
booktitle = "Proactive Assistant Agents - Papers from the AAAI Fall Symposium, Technical Report",

}

Iacobelli, F, Nichols, N, Birnbaum, LA & Hammond, KJ 2010, Finding new information via robust entity detection. in Proactive Assistant Agents - Papers from the AAAI Fall Symposium, Technical Report. vol. FS-10-07, pp. 32-37, 2010 AAAI Fall Symposium, Arlington, VA, United States, 11/11/10.

Finding new information via robust entity detection. / Iacobelli, Francisco; Nichols, Nathan; Birnbaum, Lawrence A; Hammond, Kristian J.

Proactive Assistant Agents - Papers from the AAAI Fall Symposium, Technical Report. Vol. FS-10-07 2010. p. 32-37.

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

TY - GEN

T1 - Finding new information via robust entity detection

AU - Iacobelli, Francisco

AU - Nichols, Nathan

AU - Birnbaum, Lawrence A

AU - Hammond, Kristian J

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Journalists and editors work under pressure to collect relevant details and background information about specific events. They spend a significant amount of time sifting through documents and finding new information such as facts, opinions or stakeholders (i.e. people, places and organizations that have a stake in the news). Spotting them is a tedious and cognitively intense process. One task, essential to this process, is to find and keep track of stakeholders. This task is taxing cognitively and in terms of memory. Tell Me More offers an automatic aid to this task. Tell Me More is a system that, given a seed story, mines the web for similar stories reported by different sources and selects only those stories which offer new information with respect to that original seed story. Much like a journalist, the task of detecting named entities is central to its success. In this paper we briefly describe Tell Me More and, in particular, we focus on Tell Me More's entity detection component. We describe an approach that combines off-the-shelf named entity recognizers (NERs) with WPED, an in-house publicly available NER that uses Wikipedia as its knowledge base. We show significant increase in precision scores with respect to traditional NERs. Lastly, we present an overall evaluation of Tell Me More using this approach.

AB - Journalists and editors work under pressure to collect relevant details and background information about specific events. They spend a significant amount of time sifting through documents and finding new information such as facts, opinions or stakeholders (i.e. people, places and organizations that have a stake in the news). Spotting them is a tedious and cognitively intense process. One task, essential to this process, is to find and keep track of stakeholders. This task is taxing cognitively and in terms of memory. Tell Me More offers an automatic aid to this task. Tell Me More is a system that, given a seed story, mines the web for similar stories reported by different sources and selects only those stories which offer new information with respect to that original seed story. Much like a journalist, the task of detecting named entities is central to its success. In this paper we briefly describe Tell Me More and, in particular, we focus on Tell Me More's entity detection component. We describe an approach that combines off-the-shelf named entity recognizers (NERs) with WPED, an in-house publicly available NER that uses Wikipedia as its knowledge base. We show significant increase in precision scores with respect to traditional NERs. Lastly, we present an overall evaluation of Tell Me More using this approach.

UR - http://www.scopus.com/inward/record.url?scp=79960116567&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960116567&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781577354895

VL - FS-10-07

SP - 32

EP - 37

BT - Proactive Assistant Agents - Papers from the AAAI Fall Symposium, Technical Report

ER -

Iacobelli F, Nichols N, Birnbaum LA, Hammond KJ. Finding new information via robust entity detection. In Proactive Assistant Agents - Papers from the AAAI Fall Symposium, Technical Report. Vol. FS-10-07. 2010. p. 32-37