@inproceedings{remus-ziegelmayer-2014-learning,
title = "Learning from Domain Complexity",
author = "Remus, Robert and
Ziegelmayer, Dominique",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/480_Paper.pdf",
pages = "2021--2028",
abstract = "Sentiment analysis is genre and domain dependent, i.e. the same method performs differently when applied to text that originates from different genres and domains. Intuitively, this is due to different language use in different genres and domains. We measure such differences in a sentiment analysis gold standard dataset that contains texts from 1 genre and 10 domains. Differences in language use are quantified using certain language statistics, viz. domain complexity measures. We investigate 4 domain complexity measures: percentage of rare words, word richness, relative entropy and corpus homogeneity. We relate domain complexity measurements to performance of a standard machine learning-based classifier and find strong correlations. We show that we can accurately estimate its performance based on domain complexity using linear regression models fitted using robust loss functions. Moreover, we illustrate how domain complexity may guide us in model selection, viz. in deciding what word n-gram order to employ in a discriminative model and whether to employ aggressive or conservative word n-gram feature selection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="remus-ziegelmayer-2014-learning">
<titleInfo>
<title>Learning from Domain Complexity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Remus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominique</namePart>
<namePart type="family">Ziegelmayer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sentiment analysis is genre and domain dependent, i.e. the same method performs differently when applied to text that originates from different genres and domains. Intuitively, this is due to different language use in different genres and domains. We measure such differences in a sentiment analysis gold standard dataset that contains texts from 1 genre and 10 domains. Differences in language use are quantified using certain language statistics, viz. domain complexity measures. We investigate 4 domain complexity measures: percentage of rare words, word richness, relative entropy and corpus homogeneity. We relate domain complexity measurements to performance of a standard machine learning-based classifier and find strong correlations. We show that we can accurately estimate its performance based on domain complexity using linear regression models fitted using robust loss functions. Moreover, we illustrate how domain complexity may guide us in model selection, viz. in deciding what word n-gram order to employ in a discriminative model and whether to employ aggressive or conservative word n-gram feature selection.</abstract>
<identifier type="citekey">remus-ziegelmayer-2014-learning</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/480_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2021</start>
<end>2028</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning from Domain Complexity
%A Remus, Robert
%A Ziegelmayer, Dominique
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F remus-ziegelmayer-2014-learning
%X Sentiment analysis is genre and domain dependent, i.e. the same method performs differently when applied to text that originates from different genres and domains. Intuitively, this is due to different language use in different genres and domains. We measure such differences in a sentiment analysis gold standard dataset that contains texts from 1 genre and 10 domains. Differences in language use are quantified using certain language statistics, viz. domain complexity measures. We investigate 4 domain complexity measures: percentage of rare words, word richness, relative entropy and corpus homogeneity. We relate domain complexity measurements to performance of a standard machine learning-based classifier and find strong correlations. We show that we can accurately estimate its performance based on domain complexity using linear regression models fitted using robust loss functions. Moreover, we illustrate how domain complexity may guide us in model selection, viz. in deciding what word n-gram order to employ in a discriminative model and whether to employ aggressive or conservative word n-gram feature selection.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/480_Paper.pdf
%P 2021-2028
Markdown (Informal)
[Learning from Domain Complexity](http://www.lrec-conf.org/proceedings/lrec2014/pdf/480_Paper.pdf) (Remus & Ziegelmayer, LREC 2014)
ACL
- Robert Remus and Dominique Ziegelmayer. 2014. Learning from Domain Complexity. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2021–2028, Reykjavik, Iceland. European Language Resources Association (ELRA).