@inproceedings{orasmaa-etal-2016-estnltk,
title = "{E}st{NLTK} - {NLP} Toolkit for {E}stonian",
author = "Orasmaa, Siim and
Petmanson, Timo and
Tkachenko, Alexander and
Laur, Sven and
Kaalep, Heiki-Jaan",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1390",
pages = "2460--2466",
abstract = "Although there are many tools for natural language processing tasks in Estonian, these tools are very loosely interoperable, and it is not easy to build practical applications on top of them. In this paper, we introduce a new Python library for natural language processing in Estonian, which provides unified programming interface for various NLP components. The EstNLTK toolkit provides utilities for basic NLP tasks including tokenization, morphological analysis, lemmatisation and named entity recognition as well as offers more advanced features such as a clause segmentation, temporal expression extraction and normalization, verb chain detection, Estonian Wordnet integration and rule-based information extraction. Accompanied by a detailed API documentation and comprehensive tutorials, EstNLTK is suitable for a wide range of audience. We believe EstNLTK is mature enough to be used for developing NLP-backed systems both in industry and research. EstNLTK is freely available under the GNU GPL version 2+ license, which is standard for academic software.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="orasmaa-etal-2016-estnltk">
<titleInfo>
<title>EstNLTK - NLP Toolkit for Estonian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siim</namePart>
<namePart type="family">Orasmaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timo</namePart>
<namePart type="family">Petmanson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Tkachenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sven</namePart>
<namePart type="family">Laur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heiki-Jaan</namePart>
<namePart type="family">Kaalep</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although there are many tools for natural language processing tasks in Estonian, these tools are very loosely interoperable, and it is not easy to build practical applications on top of them. In this paper, we introduce a new Python library for natural language processing in Estonian, which provides unified programming interface for various NLP components. The EstNLTK toolkit provides utilities for basic NLP tasks including tokenization, morphological analysis, lemmatisation and named entity recognition as well as offers more advanced features such as a clause segmentation, temporal expression extraction and normalization, verb chain detection, Estonian Wordnet integration and rule-based information extraction. Accompanied by a detailed API documentation and comprehensive tutorials, EstNLTK is suitable for a wide range of audience. We believe EstNLTK is mature enough to be used for developing NLP-backed systems both in industry and research. EstNLTK is freely available under the GNU GPL version 2+ license, which is standard for academic software.</abstract>
<identifier type="citekey">orasmaa-etal-2016-estnltk</identifier>
<location>
<url>https://aclanthology.org/L16-1390</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2460</start>
<end>2466</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EstNLTK - NLP Toolkit for Estonian
%A Orasmaa, Siim
%A Petmanson, Timo
%A Tkachenko, Alexander
%A Laur, Sven
%A Kaalep, Heiki-Jaan
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F orasmaa-etal-2016-estnltk
%X Although there are many tools for natural language processing tasks in Estonian, these tools are very loosely interoperable, and it is not easy to build practical applications on top of them. In this paper, we introduce a new Python library for natural language processing in Estonian, which provides unified programming interface for various NLP components. The EstNLTK toolkit provides utilities for basic NLP tasks including tokenization, morphological analysis, lemmatisation and named entity recognition as well as offers more advanced features such as a clause segmentation, temporal expression extraction and normalization, verb chain detection, Estonian Wordnet integration and rule-based information extraction. Accompanied by a detailed API documentation and comprehensive tutorials, EstNLTK is suitable for a wide range of audience. We believe EstNLTK is mature enough to be used for developing NLP-backed systems both in industry and research. EstNLTK is freely available under the GNU GPL version 2+ license, which is standard for academic software.
%U https://aclanthology.org/L16-1390
%P 2460-2466
Markdown (Informal)
[EstNLTK - NLP Toolkit for Estonian](https://aclanthology.org/L16-1390) (Orasmaa et al., LREC 2016)
ACL
- Siim Orasmaa, Timo Petmanson, Alexander Tkachenko, Sven Laur, and Heiki-Jaan Kaalep. 2016. EstNLTK - NLP Toolkit for Estonian. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2460–2466, Portorož, Slovenia. European Language Resources Association (ELRA).