The semantic role labels of verb predicates can be used
to
define an event model for understanding text. In the system described in
this paper, the events are extracted from documents that are summary
reports about individual people. The system constructed for the event
extraction integrates a statistical approach using machine learning over
Propbank semantic role labels with a rule-based approach using a
sublanguage grammar of the summary reports. The event model is also
utilized in identifying patterns of event/role usage that can be mapped to
entity relations in the domain ontology of the application.
Description
Suggest to use SRL or standard statistical extraction techniques as domain independent EE solutions, then adapt with domain-dependent rules.
Aim to match events extracted from biographical text with a summary report.
Good coverage of events and arguments with PropBank-trained SRL system, plus rules for common patterns failed by SRL.
Aim to map this to domain ontologies, but have no results yet.
%0 Conference Paper
%1 mccracken2006
%A McCracken, Nancy
%A Ozgencil, Necati Ercan
%A Symonenko, Svetlana
%B Proceedings of the 2006 AAAI Workshop on EventExtractionand Synthesis
%D 2006
%K PropBank SRL dataset_own event_extraction ontology_output
%P 7--11
%T Combining Techniques for Event Extraction in Summary Reports
%U http://www.aaai.org/Papers/Workshops/2006/WS-06-07/WS06-07-003.pdf
%X The semantic role labels of verb predicates can be used
to
define an event model for understanding text. In the system described in
this paper, the events are extracted from documents that are summary
reports about individual people. The system constructed for the event
extraction integrates a statistical approach using machine learning over
Propbank semantic role labels with a rule-based approach using a
sublanguage grammar of the summary reports. The event model is also
utilized in identifying patterns of event/role usage that can be mapped to
entity relations in the domain ontology of the application.
@inproceedings{mccracken2006,
abstract = {The semantic role labels of verb predicates can be used
to
define an event model for understanding text. In the system described in
this paper, the events are extracted from documents that are summary
reports about individual people. The system constructed for the event
extraction integrates a statistical approach using machine learning over
Propbank semantic role labels with a rule-based approach using a
sublanguage grammar of the summary reports. The event model is also
utilized in identifying patterns of event/role usage that can be mapped to
entity relations in the domain ontology of the application.},
added-at = {2009-10-22T15:19:37.000+0200},
author = {McCracken, Nancy and Ozgencil, Necati Ercan and Symonenko, Svetlana},
biburl = {https://www.bibsonomy.org/bibtex/20b3538c4fae887a2b9b6d5fd8a993d19/jnothman},
booktitle = {Proceedings of the 2006 AAAI Workshop on EventExtractionand Synthesis},
description = {Suggest to use SRL or standard statistical extraction techniques as domain independent EE solutions, then adapt with domain-dependent rules.
Aim to match events extracted from biographical text with a summary report.
Good coverage of events and arguments with PropBank-trained SRL system, plus rules for common patterns failed by SRL.
Aim to map this to domain ontologies, but have no results yet.},
interhash = {ce68921452f1e387a44f759d2f1d87eb},
intrahash = {0b3538c4fae887a2b9b6d5fd8a993d19},
keywords = {PropBank SRL dataset_own event_extraction ontology_output},
pages = {7--11},
timestamp = {2009-10-22T15:19:37.000+0200},
title = {Combining Techniques for Event Extraction in Summary Reports},
url = {http://www.aaai.org/Papers/Workshops/2006/WS-06-07/WS06-07-003.pdf},
year = 2006
}