Instance of: Resource Info

Contributor	Jakub Waszczuk
Creator	Jakub Waszczuk
	Michał Lenart
Description	Nerf is a statistical tool for Named Entity Recognition (NER) based on the Conditional Random Fields (CRF) modelling method. The tool has been constructed as a part of the National Corpus of Polish project. It has been adapted to recognize tree-like structures of NEs (i.e., with recursivelly embeded NEs) using the Joined Label Tagging (JLT) method. The JLT method is a simple method of encoding NE structures as a sequence of labels. With this method various additional informations about NEs of categorical nature – type, subtype, type of derivation – can be encoded on the level of labels and subsequently recognized using the resultant CRF model. The tool can be configured to use various types of observations during the training and recognition process, for example: lexical informations from textual level, or grammatical informations from morphosyntactic level.
Rights	GPL
See Also	http://metashare.elda.org/repository/browse/bbe8ee646aff11e284b6000423bfd61cf73819a718ef48b9a9608b54de8bba8e/
Source	META-SHARE
Title	Polish Named Entity Recognition Tool
Type	Dataset
Type	Tool Service

Contact Point

Communication Info	Metashare/bbe8ee646aff11e284b6000423bfd61cf73819a718ef48b9a9608b54de8bba8e#communication Info
Given Name	Jakub
Surname	Waszczuk
Type	Contact Person
	Person
	Person Info Type

Distribution Info

Availability	Available-restricted Use
License	Delivery Channel Downloadable Fee free of charge Permission Action http://creativecommons.org/ns/ShareALike Duty Metashare/bbe8ee646aff11e284b6000423bfd61cf73819a718ef48b9a9608b54de8bba8e#permission Type Duty Permission Restrictions Of Use Same As http://www.gnu.org/copyleft/gpl.html Type Licence Info
Type	Distribution
	Distribution Info

Identification Info

Description	Nerf is a statistical tool for Named Entity Recognition (NER) based on the Conditional Random Fields (CRF) modelling method. The tool has been constructed as a part of the National Corpus of Polish project. It has been adapted to recognize tree-like structures of NEs (i.e., with recursivelly embeded NEs) using the Joined Label Tagging (JLT) method. The JLT method is a simple method of encoding NE structures as a sequence of labels. With this method various additional informations about NEs of categorical nature – type, subtype, type of derivation – can be encoded on the level of labels and subsequently recognized using the resultant CRF model. The tool can be configured to use various types of observations during the training and recognition process, for example: lexical informations from textual level, or grammatical informations from morphosyntactic level.
Distribution	Access URL http://zil.ipipan.waw.pl/Nerf Type Distribution URL
Identifier	404
Meta Share Id	NOT_DEFINED_FOR_V2
Resource Short Name	Nerf
Title	Polish Named Entity Recognition Tool
Type	Identification Info

Resource Creation Info

Creation Start Date	2010-03-01 Date
Creator	Person Info Communication Info Address Jana Kazimierza 5 City Warsaw Distribution Access URL http://zil.ipipan.waw.pl/MichalLenart Type Distribution URL Email michal.lenart@gmail.com Fax Number +48 22 38 00 510 Telephone Number +48 22 38 00 560 Type Communication Info Zip Code 01-248 Given Name Michał Position Programmer Surname Lenart Type Person Person Info Type Type Actor
	Person Info Communication Info Address Jana Kazimierza 5 City Warsaw Email waszczuk.kuba@gmail.com Fax Number +48 22 38 00 510 Telephone Number +48 22 38 00 566 Type Communication Info Zip Code 01-248 Given Name Jakub Surname Waszczuk Type Person Person Info Type Type Actor
Funding Project	Distribution Access URL http://nkjp.pl/ Type Distribution URL Funder Polish Ministry of Science and Higher Education Funding Country Poland Funding Type National Funds Project End Date 2011-06-30 Date Project Name National Corpus of Polish Project Short Name NKJP Project Start Date 2007-01-01 Date Type Project Info Type
Type	Resource Creation Info

Resource Documentation Info

Documentation	Document Unstructured Jakub Waszczuk, Katarzyna Głowińska, Agata Savary, Adam Przepiórkowski, \"Tools and methodologies for annotating syntax and named entities in the National Corpus of Polish\", Proceedings of the 2010 International Multiconference on Computer Science and Information Technology (IMCSIT). Type Documentation Info Type
Tool Documentation Type	Help Functions
Type	Resource Documentation Info

Tool Service Info

Input Info	Media Type Text Modality Type Written Language Resource Type Language Description Type Input Info
Language Dependent	false Boolean
Output Info	Media Type Text Modality Type Written Language Resource Type Lexical Conceptual Resource Type Output Info
Resource Type	Tool Service
Tool Service Creation Info	Formalism Joined Label Tagging Conditional Random Fields Implementation Language C Cython Python Type Tool Service Creation Info
Tool Service Evaluation Info	Evaluated true Boolean Evaluation Criteria Intrinsic Evaluation Details Cross validation of the Nerf tool on the NKJP corpus, with respect to the NKJP Named Entities hierarchy, yielded F-measure of 79%. Evaluation Level Diagnostic Evaluation Measure Automatic Evaluation Report Document Unstructured Results (which will be described in the NKJP book; earlier evaluation results can be found in the \"Tools and methodologies for annotating syntax and named entities in the National Corpus of Polish\", Proceedings of the 2010 International Multiconference on Computer Science and Information Technology (IMCSIT) can be acquired by running cross_validate.py script distributed with the Nerf tool. The process is described in details in the README file, also distributed with Nerf. Type Documentation Info Type Evaluation Type Black Box Evaluator Person Info Communication Info Address Jana Kazimierza 5 City Warsaw Email waszczuk.kuba@gmail.com Fax Number +48 22 38 00 510 Telephone Number +48 22 38 00 566 Type Communication Info Zip Code 01-248 Given Name Jakub Surname Waszczuk Type Person Person Info Type Type Actor Type Tool Service Evaluation Info
Tool Service Operation Info	Operating System Linux Running Environment Info Required Software Cython (version 0.14 or higher) Python (version 2.6 or higher) Type Running Environment Info Type Tool Service Operation Info
Tool Service Type	Tool
Type	Tool Service Info

Usage Info

Actual Use Info	Actual Use Nlp Applications Actual Use Details Named entity-based mention detection for the Polish coreference resolution module. Type Actual Use Info Usage Project Distribution Access URL http://zil.ipipan.waw.pl/CORE Type Distribution URL Funder National Science Centre (100%) Funding Country Poland Funding Type National Funds Project End Date 2014-04-17 Date Project Name Computer-based methods for coreference resolution in Polish texts Project Short Name CORE Project Start Date 2011-04-18 Date Type Project Info Type Usage Report Document Unstructured Ogrodniczuk M., Kopeć M. Rule-based coreference resolution module for Polish. In Proceedings of the 8th Discourse Anaphora and Anaphor Resolution Colloquium (DAARC 2011), pp. 191–200. Faro, Portugal. Type Documentation Info Type Use NLPSpecific Parsing
	Actual Use Nlp Applications Actual Use Details Recognition of Named Entities for the UIMA Language Processing Chain in ATLAS CMS. Type Actual Use Info Usage Project Distribution Access URL http://www.atlasproject.eu Type Distribution URL Funder European Commission (50%) The Polish Ministry of Science and Higher Education (50%) Funding Country Poland Funding Type Eu Funds National Funds Project End Date 2013-02-28 Date Project Name Applied Technology for Language-Aided CMS Project Short Name ATLAS Project Start Date 2010-03-01 Date Type Project Info Type Usage Report Document Unstructured Ogrodniczuk M., Przepiórkowski A. Polish Language Processing Chains for Multilingual Information Systems. G. Bouma et al. (ed.): NLDB 2012, LNCS 7337, pp. 152–157. Springer, Heidelberg. Type Documentation Info Type Use NLPSpecific Named Entity Recognition
	Actual Use Nlp Applications Actual Use Details Recognition of Named Entities in the National Corpus of Polish. Tool trained on the manually annotated million-word subcorpus has been used to annotate the entire NKJP corpus. Type Actual Use Info Usage Project Distribution Access URL http://www.nkjp.pl Type Distribution URL Funder The Polish Ministry of Science and Higher Education (100%) Funding Country Poland Funding Type National Funds Project End Date 2011-06-12 Date Project Name National Corpus of Polish Project Short Name NKJP Project Start Date 2007-12-13 Date Type Project Info Type Usage Report Document Unstructured Agata Savary, Jakub Waszczuk and Adam Przepiórkowski. 2010. Towards the Annotation of Named Entities in the National Corpus of Polish. In Proceedings of the Seventh International Conference on Language Resources and Evaluation, LREC 2010, Valletta, Malta. ELRA. Type Documentation Info Type Document Unstructured Jakub Waszczuk, Katarzyna Głowińska, Agata Savary and Adam Przepiórkowski. 2010. Tools and Methodologies for Annotating Syntax and Named Entities in the National Corpus of Polish. In Proceedings of the International Multiconference on Computer Science and Information Technology (IMCSIT 2010): Computational Linguistics – Applications (CLA’10), pages 531–539, Wisła, Poland. PTI. Type Documentation Info Type Use NLPSpecific Named Entity Recognition
Foreseen Use Info	Foreseen Use Nlp Applications Type Foreseen Use Info Use NLPSpecific Named Entity Recognition
Type	Usage Info

Version Info

Has Version	0.2
Modified	2011-10-11 Date
Type	Version Info

Metashare/bbe8ee646aff11e284b6000423bfd61cf73819a718ef48b9a9608b54de8bba8e#metadata Creator

Instance of: Actor

Is Creator of

Metashare/bbe8ee646aff11e284b6000423bfd61cf73819a718ef48b9a9608b54de8bba8e#metadata Info

Metashare/bbe8ee646aff11e284b6000423bfd61cf73819a718ef48b9a9608b54de8bba8e#Header

Instance of: Catalog Record

Issued	2014-09-23T00:39:49Z Date
Primary Topic	Polish Named Entity Recognition Tool
Set Spec	toolService:tool
	toolService