@inproceedings{scholman-etal-2022-discogem,
title = "{D}isco{G}e{M}: A Crowdsourced Corpus of Genre-Mixed Implicit Discourse Relations",
author = "Scholman, Merel and
Dong, Tianai and
Yung, Frances and
Demberg, Vera",
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-1.351",
pages = "3281--3290",
abstract = "We present DiscoGeM, a crowdsourced corpus of 6,505 implicit discourse relations from three genres: political speech, literature, and encyclopedic texts. Each instance was annotated by 10 crowd workers. Various label aggregation methods were explored to evaluate how to obtain a label that best captures the meaning inferred by the crowd annotators. The results show that a significant proportion of discourse relations in DiscoGeM are ambiguous and can express multiple relation senses. Probability distribution labels better capture these interpretations than single labels. Further, the results emphasize that text genre crucially affects the distribution of discourse relations, suggesting that genre should be included as a factor in automatic relation classification. We make available the newly created DiscoGeM corpus, as well as the dataset with all annotator-level labels. Both the corpus and the dataset can facilitate a multitude of applications and research purposes, for example to function as training data to improve the performance of automatic discourse relation parsers, as well as facilitate research into non-connective signals of discourse relations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scholman-etal-2022-discogem">
<titleInfo>
<title>DiscoGeM: A Crowdsourced Corpus of Genre-Mixed Implicit Discourse Relations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Merel</namePart>
<namePart type="family">Scholman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianai</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frances</namePart>
<namePart type="family">Yung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</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 DiscoGeM, a crowdsourced corpus of 6,505 implicit discourse relations from three genres: political speech, literature, and encyclopedic texts. Each instance was annotated by 10 crowd workers. Various label aggregation methods were explored to evaluate how to obtain a label that best captures the meaning inferred by the crowd annotators. The results show that a significant proportion of discourse relations in DiscoGeM are ambiguous and can express multiple relation senses. Probability distribution labels better capture these interpretations than single labels. Further, the results emphasize that text genre crucially affects the distribution of discourse relations, suggesting that genre should be included as a factor in automatic relation classification. We make available the newly created DiscoGeM corpus, as well as the dataset with all annotator-level labels. Both the corpus and the dataset can facilitate a multitude of applications and research purposes, for example to function as training data to improve the performance of automatic discourse relation parsers, as well as facilitate research into non-connective signals of discourse relations.</abstract>
<identifier type="citekey">scholman-etal-2022-discogem</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.351</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3281</start>
<end>3290</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DiscoGeM: A Crowdsourced Corpus of Genre-Mixed Implicit Discourse Relations
%A Scholman, Merel
%A Dong, Tianai
%A Yung, Frances
%A Demberg, Vera
%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 scholman-etal-2022-discogem
%X We present DiscoGeM, a crowdsourced corpus of 6,505 implicit discourse relations from three genres: political speech, literature, and encyclopedic texts. Each instance was annotated by 10 crowd workers. Various label aggregation methods were explored to evaluate how to obtain a label that best captures the meaning inferred by the crowd annotators. The results show that a significant proportion of discourse relations in DiscoGeM are ambiguous and can express multiple relation senses. Probability distribution labels better capture these interpretations than single labels. Further, the results emphasize that text genre crucially affects the distribution of discourse relations, suggesting that genre should be included as a factor in automatic relation classification. We make available the newly created DiscoGeM corpus, as well as the dataset with all annotator-level labels. Both the corpus and the dataset can facilitate a multitude of applications and research purposes, for example to function as training data to improve the performance of automatic discourse relation parsers, as well as facilitate research into non-connective signals of discourse relations.
%U https://aclanthology.org/2022.lrec-1.351
%P 3281-3290
Markdown (Informal)
[DiscoGeM: A Crowdsourced Corpus of Genre-Mixed Implicit Discourse Relations](https://aclanthology.org/2022.lrec-1.351) (Scholman et al., LREC 2022)
ACL