@inproceedings{straka-etal-2016-udpipe,
title = "{UDP}ipe: Trainable Pipeline for Processing {C}o{NLL}-{U} Files Performing Tokenization, Morphological Analysis, {POS} Tagging and Parsing",
author = "Straka, Milan and
Haji{\v{c}}, Jan and
Strakov{\'a}, Jana",
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/L16-1680",
pages = "4290--4297",
abstract = "Automatic natural language processing of large texts often presents recurring challenges in multiple languages: even for most advanced tasks, the texts are first processed by basic processing steps {--} from tokenization to parsing. We present an extremely simple-to-use tool consisting of one binary and one model (per language), which performs these tasks for multiple languages without the need for any other external data. UDPipe, a pipeline processing CoNLL-U-formatted files, performs tokenization, morphological analysis, part-of-speech tagging, lemmatization and dependency parsing for nearly all treebanks of Universal Dependencies 1.2 (namely, the whole pipeline is currently available for 32 out of 37 treebanks). In addition, the pipeline is easily trainable with training data in CoNLL-U format (and in some cases also with additional raw corpora) and requires minimal linguistic knowledge on the users{'} part. The training code is also released.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="straka-etal-2016-udpipe">
<titleInfo>
<title>UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Milan</namePart>
<namePart type="family">Straka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Hajič</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jana</namePart>
<namePart type="family">Straková</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>Automatic natural language processing of large texts often presents recurring challenges in multiple languages: even for most advanced tasks, the texts are first processed by basic processing steps – from tokenization to parsing. We present an extremely simple-to-use tool consisting of one binary and one model (per language), which performs these tasks for multiple languages without the need for any other external data. UDPipe, a pipeline processing CoNLL-U-formatted files, performs tokenization, morphological analysis, part-of-speech tagging, lemmatization and dependency parsing for nearly all treebanks of Universal Dependencies 1.2 (namely, the whole pipeline is currently available for 32 out of 37 treebanks). In addition, the pipeline is easily trainable with training data in CoNLL-U format (and in some cases also with additional raw corpora) and requires minimal linguistic knowledge on the users’ part. The training code is also released.</abstract>
<identifier type="citekey">straka-etal-2016-udpipe</identifier>
<location>
<url>https://aclanthology.org/L16-1680</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4290</start>
<end>4297</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing
%A Straka, Milan
%A Hajič, Jan
%A Straková, Jana
%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 straka-etal-2016-udpipe
%X Automatic natural language processing of large texts often presents recurring challenges in multiple languages: even for most advanced tasks, the texts are first processed by basic processing steps – from tokenization to parsing. We present an extremely simple-to-use tool consisting of one binary and one model (per language), which performs these tasks for multiple languages without the need for any other external data. UDPipe, a pipeline processing CoNLL-U-formatted files, performs tokenization, morphological analysis, part-of-speech tagging, lemmatization and dependency parsing for nearly all treebanks of Universal Dependencies 1.2 (namely, the whole pipeline is currently available for 32 out of 37 treebanks). In addition, the pipeline is easily trainable with training data in CoNLL-U format (and in some cases also with additional raw corpora) and requires minimal linguistic knowledge on the users’ part. The training code is also released.
%U https://aclanthology.org/L16-1680
%P 4290-4297
Markdown (Informal)
[UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing](https://aclanthology.org/L16-1680) (Straka et al., LREC 2016)
ACL