@inproceedings{hajnicz-2020-interannotator,
title = "Interannotator Agreement for Lexico-Semantic Annotation of a Corpus",
author = "Hajnicz, El{\.z}bieta",
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-1.227",
pages = "1842--1848",
abstract = "This paper examines the procedure for lexico-semantic annotation of the Basic Corpus of Polish Metaphors that is the first step for annotating metaphoric expressions occurring in it. The procedure involves correcting the morphosyntactic annotation of part of the corpus that is automatically annotated on the morphosyntactic level. The main procedure concerns annotation of adjectives, adverbs, nouns and verbs (including gerunds and participles), including abbreviations of the words that belong to the above classes. It is composed of three steps: deciding whether a particular occurrence of a word is asemantic (e.g. anaphoric or strictly grammatical), whether we are dealing with a multi-word expression, reciprocal usages of the si{\k{e}} marker and pluralia tantum, which may involve annotation with two lexical units (having two different lemmas) for a single token. We propose an interannotator agreement statistics adequate for this procedure. Finally, we discuss the preliminary results of annotation of a fragment of the corpus.",
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="hajnicz-2020-interannotator">
<titleInfo>
<title>Interannotator Agreement for Lexico-Semantic Annotation of a Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elżbieta</namePart>
<namePart type="family">Hajnicz</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>This paper examines the procedure for lexico-semantic annotation of the Basic Corpus of Polish Metaphors that is the first step for annotating metaphoric expressions occurring in it. The procedure involves correcting the morphosyntactic annotation of part of the corpus that is automatically annotated on the morphosyntactic level. The main procedure concerns annotation of adjectives, adverbs, nouns and verbs (including gerunds and participles), including abbreviations of the words that belong to the above classes. It is composed of three steps: deciding whether a particular occurrence of a word is asemantic (e.g. anaphoric or strictly grammatical), whether we are dealing with a multi-word expression, reciprocal usages of the się marker and pluralia tantum, which may involve annotation with two lexical units (having two different lemmas) for a single token. We propose an interannotator agreement statistics adequate for this procedure. Finally, we discuss the preliminary results of annotation of a fragment of the corpus.</abstract>
<identifier type="citekey">hajnicz-2020-interannotator</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.227</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1842</start>
<end>1848</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interannotator Agreement for Lexico-Semantic Annotation of a Corpus
%A Hajnicz, Elżbieta
%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 hajnicz-2020-interannotator
%X This paper examines the procedure for lexico-semantic annotation of the Basic Corpus of Polish Metaphors that is the first step for annotating metaphoric expressions occurring in it. The procedure involves correcting the morphosyntactic annotation of part of the corpus that is automatically annotated on the morphosyntactic level. The main procedure concerns annotation of adjectives, adverbs, nouns and verbs (including gerunds and participles), including abbreviations of the words that belong to the above classes. It is composed of three steps: deciding whether a particular occurrence of a word is asemantic (e.g. anaphoric or strictly grammatical), whether we are dealing with a multi-word expression, reciprocal usages of the się marker and pluralia tantum, which may involve annotation with two lexical units (having two different lemmas) for a single token. We propose an interannotator agreement statistics adequate for this procedure. Finally, we discuss the preliminary results of annotation of a fragment of the corpus.
%U https://aclanthology.org/2020.lrec-1.227
%P 1842-1848
Markdown (Informal)
[Interannotator Agreement for Lexico-Semantic Annotation of a Corpus](https://aclanthology.org/2020.lrec-1.227) (Hajnicz, LREC 2020)
ACL