@inproceedings{kanerva-ginter-2022-domain,
title = "Out-of-Domain Evaluation of {F}innish Dependency Parsing",
author = "Kanerva, Jenna and
Ginter, Filip",
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-1.120",
pages = "1114--1124",
abstract = "The prevailing practice in the academia is to evaluate the model performance on in-domain evaluation data typically set aside from the training corpus. However, in many real world applications the data on which the model is applied may very substantially differ from the characteristics of the training data. In this paper, we focus on Finnish out-of-domain parsing by introducing a novel UD Finnish-OOD out-of-domain treebank including five very distinct data sources (web documents, clinical, online discussions, tweets, and poetry), and a total of 19,382 syntactic words in 2,122 sentences released under the Universal Dependencies framework. Together with the new treebank, we present extensive out-of-domain parsing evaluation utilizing the available section-level information from three different Finnish UD treebanks (TDT, PUD, OOD). Compared to the previously existing treebanks, the new Finnish-OOD is shown include sections more challenging for the general parser, creating an interesting evaluation setting and yielding valuable information for those applying the parser outside of its training domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kanerva-ginter-2022-domain">
<titleInfo>
<title>Out-of-Domain Evaluation of Finnish Dependency Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jenna</namePart>
<namePart type="family">Kanerva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Ginter</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>The prevailing practice in the academia is to evaluate the model performance on in-domain evaluation data typically set aside from the training corpus. However, in many real world applications the data on which the model is applied may very substantially differ from the characteristics of the training data. In this paper, we focus on Finnish out-of-domain parsing by introducing a novel UD Finnish-OOD out-of-domain treebank including five very distinct data sources (web documents, clinical, online discussions, tweets, and poetry), and a total of 19,382 syntactic words in 2,122 sentences released under the Universal Dependencies framework. Together with the new treebank, we present extensive out-of-domain parsing evaluation utilizing the available section-level information from three different Finnish UD treebanks (TDT, PUD, OOD). Compared to the previously existing treebanks, the new Finnish-OOD is shown include sections more challenging for the general parser, creating an interesting evaluation setting and yielding valuable information for those applying the parser outside of its training domain.</abstract>
<identifier type="citekey">kanerva-ginter-2022-domain</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.120</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1114</start>
<end>1124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Out-of-Domain Evaluation of Finnish Dependency Parsing
%A Kanerva, Jenna
%A Ginter, Filip
%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 kanerva-ginter-2022-domain
%X The prevailing practice in the academia is to evaluate the model performance on in-domain evaluation data typically set aside from the training corpus. However, in many real world applications the data on which the model is applied may very substantially differ from the characteristics of the training data. In this paper, we focus on Finnish out-of-domain parsing by introducing a novel UD Finnish-OOD out-of-domain treebank including five very distinct data sources (web documents, clinical, online discussions, tweets, and poetry), and a total of 19,382 syntactic words in 2,122 sentences released under the Universal Dependencies framework. Together with the new treebank, we present extensive out-of-domain parsing evaluation utilizing the available section-level information from three different Finnish UD treebanks (TDT, PUD, OOD). Compared to the previously existing treebanks, the new Finnish-OOD is shown include sections more challenging for the general parser, creating an interesting evaluation setting and yielding valuable information for those applying the parser outside of its training domain.
%U https://aclanthology.org/2022.lrec-1.120
%P 1114-1124
Markdown (Informal)
[Out-of-Domain Evaluation of Finnish Dependency Parsing](https://aclanthology.org/2022.lrec-1.120) (Kanerva & Ginter, LREC 2022)
ACL