Kernel-based relation extraction from investigative data

Cristina Giannone, Roberto Basili, Chiara Del Vescovo, Paolo Naggar, Alessandro Moschitti

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

3 Citations (Scopus)

Abstract

In a specific process of business intelligence, i.e. investigation on organized crime, empirical language processing technologies can play a crucial role. In the data used on investigative activities, such as police interrogatory or electronic eavesdropping and wiretap, it is customary to find out expressions in non conventional languages as dialects, slangs or coded words. The recognition and storage of complex relations among subjects mentioned in these sources is a very dificult and time consuming task, ultimately based on pools of experts. We discuss here an inductive relation extraction platform that opens the way to much cheaper and consistent workows. SVMs here are employed to produce a set of possible interpretations for domain relevant concepts. An ontology population process is here realized, where further reasoning can be applied to proof the overall consistency of the extracted information. The empirical investigation presented here shows that accurate results, comparable to the expert teams, can be achieved, and parametrization allows to fine tune the system behavior for fitting the specific domain requirements.

Original languageEnglish
Title of host publicationACM International Conference Proceeding Series
Pages93-100
Number of pages8
DOIs
Publication statusPublished - 27 Nov 2009
Externally publishedYes
Event3rd Workshop on Analytics for Noisy Unstructured Text Data, AND 2009 - Barcelona, Spain
Duration: 23 Jul 200924 Jul 2009

Other

Other3rd Workshop on Analytics for Noisy Unstructured Text Data, AND 2009
CountrySpain
CityBarcelona
Period23/7/0924/7/09

Fingerprint

Competitive intelligence
Crime
Law enforcement
Ontology
Processing

ASJC Scopus subject areas

  • Human-Computer Interaction

Cite this

Giannone, C., Basili, R., Del Vescovo, C., Naggar, P., & Moschitti, A. (2009). Kernel-based relation extraction from investigative data. In ACM International Conference Proceeding Series (pp. 93-100) https://doi.org/10.1145/1568296.1568312

Kernel-based relation extraction from investigative data. / Giannone, Cristina; Basili, Roberto; Del Vescovo, Chiara; Naggar, Paolo; Moschitti, Alessandro.

ACM International Conference Proceeding Series. 2009. p. 93-100.

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

Giannone, C, Basili, R, Del Vescovo, C, Naggar, P & Moschitti, A 2009, Kernel-based relation extraction from investigative data. in ACM International Conference Proceeding Series. pp. 93-100, 3rd Workshop on Analytics for Noisy Unstructured Text Data, AND 2009, Barcelona, Spain, 23/7/09. https://doi.org/10.1145/1568296.1568312
Giannone C, Basili R, Del Vescovo C, Naggar P, Moschitti A. Kernel-based relation extraction from investigative data. In ACM International Conference Proceeding Series. 2009. p. 93-100 https://doi.org/10.1145/1568296.1568312
Giannone, Cristina ; Basili, Roberto ; Del Vescovo, Chiara ; Naggar, Paolo ; Moschitti, Alessandro. / Kernel-based relation extraction from investigative data. ACM International Conference Proceeding Series. 2009. pp. 93-100
@inproceedings{0c7c5864fa3743e890cbecb557b82c87,
title = "Kernel-based relation extraction from investigative data",
abstract = "In a specific process of business intelligence, i.e. investigation on organized crime, empirical language processing technologies can play a crucial role. In the data used on investigative activities, such as police interrogatory or electronic eavesdropping and wiretap, it is customary to find out expressions in non conventional languages as dialects, slangs or coded words. The recognition and storage of complex relations among subjects mentioned in these sources is a very dificult and time consuming task, ultimately based on pools of experts. We discuss here an inductive relation extraction platform that opens the way to much cheaper and consistent workows. SVMs here are employed to produce a set of possible interpretations for domain relevant concepts. An ontology population process is here realized, where further reasoning can be applied to proof the overall consistency of the extracted information. The empirical investigation presented here shows that accurate results, comparable to the expert teams, can be achieved, and parametrization allows to fine tune the system behavior for fitting the specific domain requirements.",
author = "Cristina Giannone and Roberto Basili and {Del Vescovo}, Chiara and Paolo Naggar and Alessandro Moschitti",
year = "2009",
month = "11",
day = "27",
doi = "10.1145/1568296.1568312",
language = "English",
isbn = "9781605584966",
pages = "93--100",
booktitle = "ACM International Conference Proceeding Series",

}

TY - GEN

T1 - Kernel-based relation extraction from investigative data

AU - Giannone, Cristina

AU - Basili, Roberto

AU - Del Vescovo, Chiara

AU - Naggar, Paolo

AU - Moschitti, Alessandro

PY - 2009/11/27

Y1 - 2009/11/27

N2 - In a specific process of business intelligence, i.e. investigation on organized crime, empirical language processing technologies can play a crucial role. In the data used on investigative activities, such as police interrogatory or electronic eavesdropping and wiretap, it is customary to find out expressions in non conventional languages as dialects, slangs or coded words. The recognition and storage of complex relations among subjects mentioned in these sources is a very dificult and time consuming task, ultimately based on pools of experts. We discuss here an inductive relation extraction platform that opens the way to much cheaper and consistent workows. SVMs here are employed to produce a set of possible interpretations for domain relevant concepts. An ontology population process is here realized, where further reasoning can be applied to proof the overall consistency of the extracted information. The empirical investigation presented here shows that accurate results, comparable to the expert teams, can be achieved, and parametrization allows to fine tune the system behavior for fitting the specific domain requirements.

AB - In a specific process of business intelligence, i.e. investigation on organized crime, empirical language processing technologies can play a crucial role. In the data used on investigative activities, such as police interrogatory or electronic eavesdropping and wiretap, it is customary to find out expressions in non conventional languages as dialects, slangs or coded words. The recognition and storage of complex relations among subjects mentioned in these sources is a very dificult and time consuming task, ultimately based on pools of experts. We discuss here an inductive relation extraction platform that opens the way to much cheaper and consistent workows. SVMs here are employed to produce a set of possible interpretations for domain relevant concepts. An ontology population process is here realized, where further reasoning can be applied to proof the overall consistency of the extracted information. The empirical investigation presented here shows that accurate results, comparable to the expert teams, can be achieved, and parametrization allows to fine tune the system behavior for fitting the specific domain requirements.

UR - http://www.scopus.com/inward/record.url?scp=70450159082&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70450159082&partnerID=8YFLogxK

U2 - 10.1145/1568296.1568312

DO - 10.1145/1568296.1568312

M3 - Conference contribution

AN - SCOPUS:70450159082

SN - 9781605584966

SP - 93

EP - 100

BT - ACM International Conference Proceeding Series

ER -