@inproceedings{janssen-2016-teitok,
title = "{TEITOK}: Text-Faithful Annotated Corpora",
author = "Janssen, Maarten",
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/L16-1637",
pages = "4037--4043",
abstract = "TEITOK is a web-based framework for corpus creation, annotation, and distribution, that combines textual and linguistic annotation within a single TEI based XML document. TEITOK provides several built-in NLP tools to automatically (pre)process texts, and is highly customizable. It features multiple orthographic transcription layers, and a wide range of user-defined token-based annotations. For searching, TEITOK interfaces with a local CQP server. TEITOK can handle various types of additional resources including Facsimile images and linked audio files, making it possible to have a combined written/spoken corpus. It also has additional modules for PSDX syntactic annotation and several types of stand-off annotation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="janssen-2016-teitok">
<titleInfo>
<title>TEITOK: Text-Faithful Annotated Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maarten</namePart>
<namePart type="family">Janssen</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>TEITOK is a web-based framework for corpus creation, annotation, and distribution, that combines textual and linguistic annotation within a single TEI based XML document. TEITOK provides several built-in NLP tools to automatically (pre)process texts, and is highly customizable. It features multiple orthographic transcription layers, and a wide range of user-defined token-based annotations. For searching, TEITOK interfaces with a local CQP server. TEITOK can handle various types of additional resources including Facsimile images and linked audio files, making it possible to have a combined written/spoken corpus. It also has additional modules for PSDX syntactic annotation and several types of stand-off annotation.</abstract>
<identifier type="citekey">janssen-2016-teitok</identifier>
<location>
<url>https://aclanthology.org/L16-1637</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4037</start>
<end>4043</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TEITOK: Text-Faithful Annotated Corpora
%A Janssen, Maarten
%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 janssen-2016-teitok
%X TEITOK is a web-based framework for corpus creation, annotation, and distribution, that combines textual and linguistic annotation within a single TEI based XML document. TEITOK provides several built-in NLP tools to automatically (pre)process texts, and is highly customizable. It features multiple orthographic transcription layers, and a wide range of user-defined token-based annotations. For searching, TEITOK interfaces with a local CQP server. TEITOK can handle various types of additional resources including Facsimile images and linked audio files, making it possible to have a combined written/spoken corpus. It also has additional modules for PSDX syntactic annotation and several types of stand-off annotation.
%U https://aclanthology.org/L16-1637
%P 4037-4043
Markdown (Informal)
[TEITOK: Text-Faithful Annotated Corpora](https://aclanthology.org/L16-1637) (Janssen, LREC 2016)
ACL
- Maarten Janssen. 2016. TEITOK: Text-Faithful Annotated Corpora. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4037–4043, Portorož, Slovenia. European Language Resources Association (ELRA).