@inproceedings{trips-percillier-2020-lemmatising,
title = "Lemmatising Verbs in {M}iddle {E}nglish Corpora: The Benefit of Enriching the {P}enn-{H}elsinki Parsed Corpus of {M}iddle {E}nglish 2 ({PPCME}2), the Parsed Corpus of {M}iddle {E}nglish Poetry ({PCMEP}), and A Parsed Linguistic Atlas of Early {M}iddle {E}nglish ({PLAEME})",
author = "Trips, Carola and
Percillier, Michael",
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-1.886",
pages = "7170--7178",
abstract = "This paper describes the lemmatisation of three annotated corpora of Middle English{---}the Penn-Helsinki Parsed Corpus of Middle English 2 (PPCME2), the Parsed Corpus of Middle English Poetry (PCMEP), and A Parsed Linguistic Atlas of Early Middle English (PLAEME) {---} which is a prerequisite for systematically investigating the argument structures of verbs of the given time. Creating this tool and enriching existing parsed corpora of Middle English is part of the project Borrowing of Argument Structure in Contact Situations (BASICS) which seeks to explain to which extent verbs copied from Old French had an impact on the grammar of Middle English. First, we lemmatised the PPCME2 by (1) creating an inventory of form-lemma correspondences linking forms in the PPCME2 to lemmas in the MED, and (2) inserting this lemma information into the corpus (precision: 94.85{\%}, recall: 98.92{\%}). Second, we enriched the PCMEP and PLAEME, which adopted the annotation format of the PPCME2, with verb lemmas to undertake studies that fill the well-known data gap in the subperiod (1250{--}1350) of the PPCME2. The case study of reflexives shows that with our method we gain much more reliable results in terms of diachrony, diatopy and contact-induced change.",
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="trips-percillier-2020-lemmatising">
<titleInfo>
<title>Lemmatising Verbs in Middle English Corpora: The Benefit of Enriching the Penn-Helsinki Parsed Corpus of Middle English 2 (PPCME2), the Parsed Corpus of Middle English Poetry (PCMEP), and A Parsed Linguistic Atlas of Early Middle English (PLAEME)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carola</namePart>
<namePart type="family">Trips</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Percillier</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 describes the lemmatisation of three annotated corpora of Middle English—the Penn-Helsinki Parsed Corpus of Middle English 2 (PPCME2), the Parsed Corpus of Middle English Poetry (PCMEP), and A Parsed Linguistic Atlas of Early Middle English (PLAEME) — which is a prerequisite for systematically investigating the argument structures of verbs of the given time. Creating this tool and enriching existing parsed corpora of Middle English is part of the project Borrowing of Argument Structure in Contact Situations (BASICS) which seeks to explain to which extent verbs copied from Old French had an impact on the grammar of Middle English. First, we lemmatised the PPCME2 by (1) creating an inventory of form-lemma correspondences linking forms in the PPCME2 to lemmas in the MED, and (2) inserting this lemma information into the corpus (precision: 94.85%, recall: 98.92%). Second, we enriched the PCMEP and PLAEME, which adopted the annotation format of the PPCME2, with verb lemmas to undertake studies that fill the well-known data gap in the subperiod (1250–1350) of the PPCME2. The case study of reflexives shows that with our method we gain much more reliable results in terms of diachrony, diatopy and contact-induced change.</abstract>
<identifier type="citekey">trips-percillier-2020-lemmatising</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.886</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>7170</start>
<end>7178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lemmatising Verbs in Middle English Corpora: The Benefit of Enriching the Penn-Helsinki Parsed Corpus of Middle English 2 (PPCME2), the Parsed Corpus of Middle English Poetry (PCMEP), and A Parsed Linguistic Atlas of Early Middle English (PLAEME)
%A Trips, Carola
%A Percillier, Michael
%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 trips-percillier-2020-lemmatising
%X This paper describes the lemmatisation of three annotated corpora of Middle English—the Penn-Helsinki Parsed Corpus of Middle English 2 (PPCME2), the Parsed Corpus of Middle English Poetry (PCMEP), and A Parsed Linguistic Atlas of Early Middle English (PLAEME) — which is a prerequisite for systematically investigating the argument structures of verbs of the given time. Creating this tool and enriching existing parsed corpora of Middle English is part of the project Borrowing of Argument Structure in Contact Situations (BASICS) which seeks to explain to which extent verbs copied from Old French had an impact on the grammar of Middle English. First, we lemmatised the PPCME2 by (1) creating an inventory of form-lemma correspondences linking forms in the PPCME2 to lemmas in the MED, and (2) inserting this lemma information into the corpus (precision: 94.85%, recall: 98.92%). Second, we enriched the PCMEP and PLAEME, which adopted the annotation format of the PPCME2, with verb lemmas to undertake studies that fill the well-known data gap in the subperiod (1250–1350) of the PPCME2. The case study of reflexives shows that with our method we gain much more reliable results in terms of diachrony, diatopy and contact-induced change.
%U https://aclanthology.org/2020.lrec-1.886
%P 7170-7178
Markdown (Informal)
[Lemmatising Verbs in Middle English Corpora: The Benefit of Enriching the Penn-Helsinki Parsed Corpus of Middle English 2 (PPCME2), the Parsed Corpus of Middle English Poetry (PCMEP), and A Parsed Linguistic Atlas of Early Middle English (PLAEME)](https://aclanthology.org/2020.lrec-1.886) (Trips & Percillier, LREC 2020)
ACL