@inproceedings{wroblewska-2020-towards,
title = "Towards the Conversion of {N}ational {C}orpus of {P}olish to {U}niversal {D}ependencies",
author = "Wr{\'o}blewska, Alina",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.653",
pages = "5308--5315",
abstract = "The research presented in this paper aims at enriching the manually morphosyntactically annotated part of National Corpus of Polish (NKJP1M) with a syntactic layer, i.e. dependency trees of sentences, and at converting both dependency trees and morphosyntactic annotations of particular tokens to Universal Dependencies. The dependency layer is built using a semi-automatic annotation procedure. The sentences from NKJP1M are first parsed with a dependency parser trained on Polish Dependency Bank, i.e. the largest bank of Polish dependency trees. The predicted dependency trees and the morphosyntactic annotations of tokens are then automatically converted into UD dependency graphs. NKJP1M sentences are an essential part of Polish Dependency Bank, we thus replace some automatically predicted dependency trees with their manually annotated equivalents. The final dependency treebank consists of 86K trees (including 15K gold-standard trees). A natural language pre-processing model trained on the enlarged set of (possibly noisy) dependency trees outperforms a model trained on a smaller set of the gold-standard trees in predicting part-of-speech tags, morphological features, lemmata, and labelled dependency trees",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wroblewska-2020-towards">
<titleInfo>
<title>Towards the Conversion of National Corpus of Polish to Universal Dependencies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Wróblewska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>The research presented in this paper aims at enriching the manually morphosyntactically annotated part of National Corpus of Polish (NKJP1M) with a syntactic layer, i.e. dependency trees of sentences, and at converting both dependency trees and morphosyntactic annotations of particular tokens to Universal Dependencies. The dependency layer is built using a semi-automatic annotation procedure. The sentences from NKJP1M are first parsed with a dependency parser trained on Polish Dependency Bank, i.e. the largest bank of Polish dependency trees. The predicted dependency trees and the morphosyntactic annotations of tokens are then automatically converted into UD dependency graphs. NKJP1M sentences are an essential part of Polish Dependency Bank, we thus replace some automatically predicted dependency trees with their manually annotated equivalents. The final dependency treebank consists of 86K trees (including 15K gold-standard trees). A natural language pre-processing model trained on the enlarged set of (possibly noisy) dependency trees outperforms a model trained on a smaller set of the gold-standard trees in predicting part-of-speech tags, morphological features, lemmata, and labelled dependency trees</abstract>
<identifier type="citekey">wroblewska-2020-towards</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.653</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5308</start>
<end>5315</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards the Conversion of National Corpus of Polish to Universal Dependencies
%A Wróblewska, Alina
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F wroblewska-2020-towards
%X The research presented in this paper aims at enriching the manually morphosyntactically annotated part of National Corpus of Polish (NKJP1M) with a syntactic layer, i.e. dependency trees of sentences, and at converting both dependency trees and morphosyntactic annotations of particular tokens to Universal Dependencies. The dependency layer is built using a semi-automatic annotation procedure. The sentences from NKJP1M are first parsed with a dependency parser trained on Polish Dependency Bank, i.e. the largest bank of Polish dependency trees. The predicted dependency trees and the morphosyntactic annotations of tokens are then automatically converted into UD dependency graphs. NKJP1M sentences are an essential part of Polish Dependency Bank, we thus replace some automatically predicted dependency trees with their manually annotated equivalents. The final dependency treebank consists of 86K trees (including 15K gold-standard trees). A natural language pre-processing model trained on the enlarged set of (possibly noisy) dependency trees outperforms a model trained on a smaller set of the gold-standard trees in predicting part-of-speech tags, morphological features, lemmata, and labelled dependency trees
%U https://aclanthology.org/2020.lrec-1.653
%P 5308-5315
Markdown (Informal)
[Towards the Conversion of National Corpus of Polish to Universal Dependencies](https://aclanthology.org/2020.lrec-1.653) (Wróblewska, LREC 2020)
ACL