Performing Named Entity Recognition on ancient documents is a
time-consuming, complex and error-prone manual task. It is a prerequisite
though to being able to identify related documents and correlate between named
entities in distinct sources, helping to precisely recreate historic events. In
order to reduce the manual effort, automated classification approaches could be
leveraged. Classifying terms in ancient documents in an automated manner poses
a difficult task due to the sources' challenging syntax and poor conservation
states. This paper introduces and evaluates two approaches that can cope with
complex syntactial environments by using statistical information derived
from a term's context and combining it with domain-specific heuristic knowledge
to perform a classification. Furthermore, these approaches can easily be
adapted to new domains.
%0 Conference Paper
%1 DBLP:conf/ic3k/SchonebergM12
%A Schöneberg, Hendrik
%A Müller, Frank
%B KDIR
%D 2012
%E Fred, Ana L. N.
%E Filipe, Joaquim
%E Fred, Ana L. N.
%E Filipe, Joaquim
%I SciTePress
%K myown
%P 163-168
%T Contextual Approaches for Identification of Toponyms in
Ancient Documents
%X Performing Named Entity Recognition on ancient documents is a
time-consuming, complex and error-prone manual task. It is a prerequisite
though to being able to identify related documents and correlate between named
entities in distinct sources, helping to precisely recreate historic events. In
order to reduce the manual effort, automated classification approaches could be
leveraged. Classifying terms in ancient documents in an automated manner poses
a difficult task due to the sources' challenging syntax and poor conservation
states. This paper introduces and evaluates two approaches that can cope with
complex syntactial environments by using statistical information derived
from a term's context and combining it with domain-specific heuristic knowledge
to perform a classification. Furthermore, these approaches can easily be
adapted to new domains.
%@ 978-989-8565-29-7
@inproceedings{DBLP:conf/ic3k/SchonebergM12,
abstract = {Performing \emph{Named Entity Recognition} on ancient documents is a
time-consuming, complex and error-prone manual task. It is a prerequisite
though to being able to identify related documents and correlate between named
entities in distinct sources, helping to precisely recreate historic events. In
order to reduce the manual effort, automated classification approaches could be
leveraged. Classifying terms in ancient documents in an automated manner poses
a difficult task due to the sources' challenging syntax and poor conservation
states. This paper introduces and evaluates two approaches that can cope with
complex syntactial environments by using statistical information derived
from a term's context and combining it with domain-specific heuristic knowledge
to perform a classification. Furthermore, these approaches can easily be
adapted to new domains.},
added-at = {2013-02-15T12:38:30.000+0100},
author = {Sch{\"o}neberg, Hendrik and M{\"u}ller, Frank},
bibsource = {DBLP, http://dblp.uni-trier.de},
biburl = {https://www.bibsonomy.org/bibtex/240e0b86fabbc2002adc172afebdc63d8/info2},
booktitle = {KDIR},
crossref = {DBLP:conf/ic3k/2012kdir},
editor = {Fred, Ana L. N. and Filipe, Joaquim and Fred, Ana L. N. and Filipe, Joaquim},
interhash = {dda9307bbf413d19482e2d9400de1874},
intrahash = {40e0b86fabbc2002adc172afebdc63d8},
isbn = {978-989-8565-29-7},
keywords = {myown},
pages = {163-168},
publisher = {SciTePress},
timestamp = {2013-02-15T13:40:56.000+0100},
title = {Contextual Approaches for Identification of Toponyms in
Ancient Documents},
year = 2012
}