Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Person Name Extraction From Turkish Financial News Text Using Local Grammar-Based Approach
Date
2008-10-29
Author
Bayraktar, Oezkan
Taşkaya Temizel, Tuğba
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
47
views
0
downloads
Cite This
Local grammar approach relies on constructing polylexical units having frozen characteristics. It has recently been shown to be superior to other named entity extraction approaches including the probabilistic, the symbolic, and the hybrid approach in terms of being able to work with untagged corpora and has successfully been applied to English, Portuguese, Korean, French and Chinese texts. In this paper, we evaluated local grammar-based approach on Turkish financial texts. We have found that although the method is successful in finding person names, the construction of frozen expressions for person name extraction is rather difficult, which can be attributed to that of Turkish word formations.
Subject Keywords
Data mining
,
Natural languages
,
Vocabulary
,
Information systems
,
Informatics
,
Pattern recognition
,
Machine learning
,
Dictionaries
,
Testing
URI
https://hdl.handle.net/11511/53833
Collections
Graduate School of Informatics, Conference / Seminar
Suggestions
OpenMETU
Core
Regional ionosphere mapping by using neural networks
Gueruen, Melike; Akdogan, Kurtulu Erinc; YILMAZ, ATİLA (2007-06-16)
Regional ionosphere mapping is necessary to understand the underlying characteristics of ionosphere. In this paper, multilayer perceptrons and radial basis networks, as chosen neural network methods, are used to obtain a map of ionosphere based on a number of given (Total Electron Content) TEC values. For varying number of given data and locations, their performances are analyzed and compared. Their performances are also tested for artificially formed data points and they are applied to real data from GPS s...
Evaluation of Site Response with Alternative Methods A Case Study for Engineering Implications
Şişman, Nurten; Askan Gündoğan, Ayşegül (null; 2016-09-23)
n this paper, efficiency of alternative geophysical techniques for site response is evaluated in two sedimentary basins on the North Anatolian Fault Zone. For this purpose, fundamental frequencies of soils and corresponding amplitudes obtained from empirical horizontal-to-vertical spectral ratio curves from microtremors, weak motions and strong motions are compared with results from one-dimensional theoretical transfer functions. Theoretical transfer functions are computed using S-wave velocity profiles der...
Human activity classification using spatio-temporal feature relations
Akpınar, Kutalmış; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2012)
This thesis compares the state of the art methods and proposes solutions for human activity classification from video data. Human activity classification is finding the meaning of human activities, which are captured by the video. Classification of human activity is needed in order to improve surveillance video analysis and summarization, video data mining and robot intelligence. This thesis focuses on the classification of low level human activities which are used as an important information source to dete...
Site-dependent spectra derived from ground motion records in Turkey
Kalkan, E; Gulkan, P (SAGE Publications, 2004-11-01)
The current spectral shapes in the Turkish Seismic Code (TSC) are based on broadly described geological conditions, ignoring fault distance or magnitude dependencies on spectral ordinates. To address this deficiency, a data set created from a suite of 112 strong ground motion records from 57 earthquakes that occurred between 1976 and 2003 has been used to develop horizontal attenuation relationships for Turkey. This way it is possible to construct hazard-consistent design spectra for any national seismic re...
Analysis of long term trends of precipitation estimates acquired using radar network in Turkey
Yılmaz, Mustafa Tuğrul; Yücel, İsmail; Yılmaz, Koray Kamil (null; 2016-04-17)
Precipitation estimates, a vital input in many hydrological and agricultural studies, can be obtained using many different platforms (ground station-, radar-, model-, satellite-based). Satellite- and model-based estimates are spatially continuous datasets, however they lack the high resolution information many applications often require. Station-based values are actual precipitation observations, however they suffer from their nature that they are point data. These datasets may be interpolated however such ...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
O. Bayraktar and T. Taşkaya Temizel, “Person Name Extraction From Turkish Financial News Text Using Local Grammar-Based Approach,” 2008, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/53833.