@inproceedings{barbu-etal-2022-aligning,
title = "Aligning the {R}omanian Reference Treebank and the Valence Lexicon of {R}omanian Verbs",
author = "Barbu, Ana-Maria and
Barbu Mititelu, Verginica and
Mititelu, C{\u{a}}t{\u{a}}lin",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.714",
pages = "6626--6634",
abstract = "We present here the efforts of aligning two language resources for Romanian: the Romanian Reference Treebank and the Valence Lexicon of Romanian Verbs: for each occurrence of those verbs in the treebank that were included as entries in the lexicon, a set of valence frames is automatically assigned, then manually validated by two linguists and, when necessary, corrected. Validating a valence frame also means semantically disambiguating the verb in the respective context. The validation is done by two linguists, on complementary datasets. However, a subset of verbs were validated by both annotators and Cohen{'}s κ is 0.87 for this subset. The alignment we have made also serves as a method of enhancing the quality of the two resources, as in the process we identify morpho-syntactic annotation mistakes, incomplete valence frames or missing ones. Information from each resource complements the information from the other, thus their value increases. The treebank and the lexicon are freely available, while the links discovered between them are also made available on GitHub.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barbu-etal-2022-aligning">
<titleInfo>
<title>Aligning the Romanian Reference Treebank and the Valence Lexicon of Romanian Verbs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ana-Maria</namePart>
<namePart type="family">Barbu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verginica</namePart>
<namePart type="family">Barbu Mititelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cătălin</namePart>
<namePart type="family">Mititelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>We present here the efforts of aligning two language resources for Romanian: the Romanian Reference Treebank and the Valence Lexicon of Romanian Verbs: for each occurrence of those verbs in the treebank that were included as entries in the lexicon, a set of valence frames is automatically assigned, then manually validated by two linguists and, when necessary, corrected. Validating a valence frame also means semantically disambiguating the verb in the respective context. The validation is done by two linguists, on complementary datasets. However, a subset of verbs were validated by both annotators and Cohen’s κ is 0.87 for this subset. The alignment we have made also serves as a method of enhancing the quality of the two resources, as in the process we identify morpho-syntactic annotation mistakes, incomplete valence frames or missing ones. Information from each resource complements the information from the other, thus their value increases. The treebank and the lexicon are freely available, while the links discovered between them are also made available on GitHub.</abstract>
<identifier type="citekey">barbu-etal-2022-aligning</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.714</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6626</start>
<end>6634</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aligning the Romanian Reference Treebank and the Valence Lexicon of Romanian Verbs
%A Barbu, Ana-Maria
%A Barbu Mititelu, Verginica
%A Mititelu, Cătălin
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F barbu-etal-2022-aligning
%X We present here the efforts of aligning two language resources for Romanian: the Romanian Reference Treebank and the Valence Lexicon of Romanian Verbs: for each occurrence of those verbs in the treebank that were included as entries in the lexicon, a set of valence frames is automatically assigned, then manually validated by two linguists and, when necessary, corrected. Validating a valence frame also means semantically disambiguating the verb in the respective context. The validation is done by two linguists, on complementary datasets. However, a subset of verbs were validated by both annotators and Cohen’s κ is 0.87 for this subset. The alignment we have made also serves as a method of enhancing the quality of the two resources, as in the process we identify morpho-syntactic annotation mistakes, incomplete valence frames or missing ones. Information from each resource complements the information from the other, thus their value increases. The treebank and the lexicon are freely available, while the links discovered between them are also made available on GitHub.
%U https://aclanthology.org/2022.lrec-1.714
%P 6626-6634
Markdown (Informal)
[Aligning the Romanian Reference Treebank and the Valence Lexicon of Romanian Verbs](https://aclanthology.org/2022.lrec-1.714) (Barbu et al., LREC 2022)
ACL