@inproceedings{walker-etal-2012-annotated,
title = "An Annotated Corpus of Film Dialogue for Learning and Characterizing Character Style",
author = "Walker, Marilyn and
Lin, Grace and
Sawyer, Jennifer",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/1114_Paper.pdf",
pages = "1373--1378",
abstract = "Interactive story systems often involve dialogue with virtual dramatic characters. However, to date most character dialogue is written by hand. One way to ease the authoring process is to (semi-)automatically generate dialogue based on film characters. We extract features from dialogue of film characters in leading roles. Then we use these character-based features to drive our language generator to produce interesting utterances. This paper describes a corpus of film dialogue that we have collected from the IMSDb archive and annotated for linguistic structures and character archetypes. We extract different sets of features using external sources such as LIWC and SentiWordNet as well as using our own written scripts. The automation of feature extraction also eases the process of acquiring additional film scripts. We briefly show how film characters can be represented by models learned from the corpus, how the models can be distinguished based on different categories such as gender and film genre, and how they can be applied to a language generator to generate utterances that can be perceived as being similar to the intended character model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="walker-etal-2012-annotated">
<titleInfo>
<title>An Annotated Corpus of Film Dialogue for Learning and Characterizing Character Style</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marilyn</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grace</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Sawyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Interactive story systems often involve dialogue with virtual dramatic characters. However, to date most character dialogue is written by hand. One way to ease the authoring process is to (semi-)automatically generate dialogue based on film characters. We extract features from dialogue of film characters in leading roles. Then we use these character-based features to drive our language generator to produce interesting utterances. This paper describes a corpus of film dialogue that we have collected from the IMSDb archive and annotated for linguistic structures and character archetypes. We extract different sets of features using external sources such as LIWC and SentiWordNet as well as using our own written scripts. The automation of feature extraction also eases the process of acquiring additional film scripts. We briefly show how film characters can be represented by models learned from the corpus, how the models can be distinguished based on different categories such as gender and film genre, and how they can be applied to a language generator to generate utterances that can be perceived as being similar to the intended character model.</abstract>
<identifier type="citekey">walker-etal-2012-annotated</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1114_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1373</start>
<end>1378</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Annotated Corpus of Film Dialogue for Learning and Characterizing Character Style
%A Walker, Marilyn
%A Lin, Grace
%A Sawyer, Jennifer
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F walker-etal-2012-annotated
%X Interactive story systems often involve dialogue with virtual dramatic characters. However, to date most character dialogue is written by hand. One way to ease the authoring process is to (semi-)automatically generate dialogue based on film characters. We extract features from dialogue of film characters in leading roles. Then we use these character-based features to drive our language generator to produce interesting utterances. This paper describes a corpus of film dialogue that we have collected from the IMSDb archive and annotated for linguistic structures and character archetypes. We extract different sets of features using external sources such as LIWC and SentiWordNet as well as using our own written scripts. The automation of feature extraction also eases the process of acquiring additional film scripts. We briefly show how film characters can be represented by models learned from the corpus, how the models can be distinguished based on different categories such as gender and film genre, and how they can be applied to a language generator to generate utterances that can be perceived as being similar to the intended character model.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1114_Paper.pdf
%P 1373-1378
Markdown (Informal)
[An Annotated Corpus of Film Dialogue for Learning and Characterizing Character Style](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1114_Paper.pdf) (Walker et al., LREC 2012)
ACL