@inproceedings{de-kuthy-etal-2016-focus-annotation,
title = "Focus Annotation of Task-based Data: A Comparison of Expert and Crowd-Sourced Annotation in a Reading Comprehension Corpus",
author = "De Kuthy, Kordula and
Ziai, Ramon and
Meurers, Detmar",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1621",
pages = "3928--3935",
abstract = "While the formal pragmatic concepts in information structure, such as the focus of an utterance, are precisely defined in theoretical linguistics and potentially very useful in conceptual and practical terms, it has turned out to be difficult to reliably annotate such notions in corpus data. We present a large-scale focus annotation effort designed to overcome this problem. Our annotation study is based on the tasked-based corpus CREG, which consists of answers to explicitly given reading comprehension questions. We compare focus annotation by trained annotators with a crowd-sourcing setup making use of untrained native speakers. Given the task context and an annotation process incrementally making the question form and answer type explicit, the trained annotators reach substantial agreement for focus annotation. Interestingly, the crowd-sourcing setup also supports high-quality annotation ― for specific subtypes of data. Finally, we turn to the question whether the relevance of focus annotation can be extrinsically evaluated. We show that automatic short-answer assessment significantly improves for focus annotated data. The focus annotated CREG corpus is freely available and constitutes the largest such resource for German.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-kuthy-etal-2016-focus-annotation">
<titleInfo>
<title>Focus Annotation of Task-based Data: A Comparison of Expert and Crowd-Sourced Annotation in a Reading Comprehension Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kordula</namePart>
<namePart type="family">De Kuthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramon</namePart>
<namePart type="family">Ziai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Detmar</namePart>
<namePart type="family">Meurers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While the formal pragmatic concepts in information structure, such as the focus of an utterance, are precisely defined in theoretical linguistics and potentially very useful in conceptual and practical terms, it has turned out to be difficult to reliably annotate such notions in corpus data. We present a large-scale focus annotation effort designed to overcome this problem. Our annotation study is based on the tasked-based corpus CREG, which consists of answers to explicitly given reading comprehension questions. We compare focus annotation by trained annotators with a crowd-sourcing setup making use of untrained native speakers. Given the task context and an annotation process incrementally making the question form and answer type explicit, the trained annotators reach substantial agreement for focus annotation. Interestingly, the crowd-sourcing setup also supports high-quality annotation ― for specific subtypes of data. Finally, we turn to the question whether the relevance of focus annotation can be extrinsically evaluated. We show that automatic short-answer assessment significantly improves for focus annotated data. The focus annotated CREG corpus is freely available and constitutes the largest such resource for German.</abstract>
<identifier type="citekey">de-kuthy-etal-2016-focus-annotation</identifier>
<location>
<url>https://aclanthology.org/L16-1621</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3928</start>
<end>3935</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Focus Annotation of Task-based Data: A Comparison of Expert and Crowd-Sourced Annotation in a Reading Comprehension Corpus
%A De Kuthy, Kordula
%A Ziai, Ramon
%A Meurers, Detmar
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F de-kuthy-etal-2016-focus-annotation
%X While the formal pragmatic concepts in information structure, such as the focus of an utterance, are precisely defined in theoretical linguistics and potentially very useful in conceptual and practical terms, it has turned out to be difficult to reliably annotate such notions in corpus data. We present a large-scale focus annotation effort designed to overcome this problem. Our annotation study is based on the tasked-based corpus CREG, which consists of answers to explicitly given reading comprehension questions. We compare focus annotation by trained annotators with a crowd-sourcing setup making use of untrained native speakers. Given the task context and an annotation process incrementally making the question form and answer type explicit, the trained annotators reach substantial agreement for focus annotation. Interestingly, the crowd-sourcing setup also supports high-quality annotation ― for specific subtypes of data. Finally, we turn to the question whether the relevance of focus annotation can be extrinsically evaluated. We show that automatic short-answer assessment significantly improves for focus annotated data. The focus annotated CREG corpus is freely available and constitutes the largest such resource for German.
%U https://aclanthology.org/L16-1621
%P 3928-3935
Markdown (Informal)
[Focus Annotation of Task-based Data: A Comparison of Expert and Crowd-Sourced Annotation in a Reading Comprehension Corpus](https://aclanthology.org/L16-1621) (De Kuthy et al., LREC 2016)
ACL