@inproceedings{xiao-etal-2020-tv,
title = "{TV}-{A}f{D}: An Imperative-Annotated Corpus from The Big Bang Theory and {W}ikipedia{'}s Articles for Deletion Discussions",
author = "Xiao, Yimin and
Slaton, Zong-Ying and
Xiao, Lu",
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-1.805",
pages = "6542--6548",
abstract = "In this study, we created an imperative corpus with speech conversations from dialogues in The Big Bang Theory and with the written comments in Wikipedia{'}s Articles for Deletion discussions. For the TV show data, 59 episodes containing 25,076 statements are used. We manually annotated imperatives based on the annotation guideline adapted from Condoravdi and Lauer{'}s study (2012) and used the retrieved data to assess the performance of syntax-based classification rules. For the Wikipedia AfD comments data, we first developed and leveraged a syntax-based classifier to extract 10,624 statements that may be imperative, and we manually examined the statements and then identified true positives. With this corpus, we also examined the performance of the rule-based imperative detection tool. Our result shows different outcomes for speech (dialogue) and written data. The rule-based classification performs better in the written data in precision (0.80) compared to the speech data (0.44). Also, the rule-based classification has a low-performance overall for speech data with the precision of 0.44, recall of 0.41, and f-1 measure of 0.42. This finding implies the syntax-based model may need to be adjusted for a speech dataset because imperatives in oral communication have greater syntactic varieties and are highly context-dependent.",
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="xiao-etal-2020-tv">
<titleInfo>
<title>TV-AfD: An Imperative-Annotated Corpus from The Big Bang Theory and Wikipedia’s Articles for Deletion Discussions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimin</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zong-Ying</namePart>
<namePart type="family">Slaton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Xiao</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>In this study, we created an imperative corpus with speech conversations from dialogues in The Big Bang Theory and with the written comments in Wikipedia’s Articles for Deletion discussions. For the TV show data, 59 episodes containing 25,076 statements are used. We manually annotated imperatives based on the annotation guideline adapted from Condoravdi and Lauer’s study (2012) and used the retrieved data to assess the performance of syntax-based classification rules. For the Wikipedia AfD comments data, we first developed and leveraged a syntax-based classifier to extract 10,624 statements that may be imperative, and we manually examined the statements and then identified true positives. With this corpus, we also examined the performance of the rule-based imperative detection tool. Our result shows different outcomes for speech (dialogue) and written data. The rule-based classification performs better in the written data in precision (0.80) compared to the speech data (0.44). Also, the rule-based classification has a low-performance overall for speech data with the precision of 0.44, recall of 0.41, and f-1 measure of 0.42. This finding implies the syntax-based model may need to be adjusted for a speech dataset because imperatives in oral communication have greater syntactic varieties and are highly context-dependent.</abstract>
<identifier type="citekey">xiao-etal-2020-tv</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.805</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6542</start>
<end>6548</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TV-AfD: An Imperative-Annotated Corpus from The Big Bang Theory and Wikipedia’s Articles for Deletion Discussions
%A Xiao, Yimin
%A Slaton, Zong-Ying
%A Xiao, Lu
%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 xiao-etal-2020-tv
%X In this study, we created an imperative corpus with speech conversations from dialogues in The Big Bang Theory and with the written comments in Wikipedia’s Articles for Deletion discussions. For the TV show data, 59 episodes containing 25,076 statements are used. We manually annotated imperatives based on the annotation guideline adapted from Condoravdi and Lauer’s study (2012) and used the retrieved data to assess the performance of syntax-based classification rules. For the Wikipedia AfD comments data, we first developed and leveraged a syntax-based classifier to extract 10,624 statements that may be imperative, and we manually examined the statements and then identified true positives. With this corpus, we also examined the performance of the rule-based imperative detection tool. Our result shows different outcomes for speech (dialogue) and written data. The rule-based classification performs better in the written data in precision (0.80) compared to the speech data (0.44). Also, the rule-based classification has a low-performance overall for speech data with the precision of 0.44, recall of 0.41, and f-1 measure of 0.42. This finding implies the syntax-based model may need to be adjusted for a speech dataset because imperatives in oral communication have greater syntactic varieties and are highly context-dependent.
%U https://aclanthology.org/2020.lrec-1.805
%P 6542-6548
Markdown (Informal)
[TV-AfD: An Imperative-Annotated Corpus from The Big Bang Theory and Wikipedia’s Articles for Deletion Discussions](https://aclanthology.org/2020.lrec-1.805) (Xiao et al., LREC 2020)
ACL