@inproceedings{bos-2008-lets,
title = "Let{'}s not Argue about Semantics",
author = "Bos, Johan",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/721_paper.pdf",
abstract = "Whats the best way to assess the performance of a semantic component in an NLP system? Tradition in NLP evaluation tells us that comparing output against a gold standard is a good idea. To define a gold standard, one first needs to decide on the representation language, and in many cases a first-order language seems a good compromise between expressive power and efficiency. Secondly, one needs to decide how to represent the various semantic phenomena, in particular the depth of analysis of quantification, plurals, eventualities, thematic roles, scope, anaphora, presupposition, ellipsis, comparatives, superlatives, tense, aspect, and time-expressions. Hence it will be hard to come up with an annotation scheme unless one permits different level of semantic granularity. The alternative is a theory-neutral black-box type evaluation where we just look at how systems react on various inputs. For this approach, we can consider the well-known task of recognising textual entailment, or the lesser-known task of textual model checking. The disadvantage of black-box methods is that it is difficult to come up with natural data that cover specific semantic phenomena.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bos-2008-lets">
<titleInfo>
<title>Let’s not Argue about Semantics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Johan</namePart>
<namePart type="family">Bos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Whats the best way to assess the performance of a semantic component in an NLP system? Tradition in NLP evaluation tells us that comparing output against a gold standard is a good idea. To define a gold standard, one first needs to decide on the representation language, and in many cases a first-order language seems a good compromise between expressive power and efficiency. Secondly, one needs to decide how to represent the various semantic phenomena, in particular the depth of analysis of quantification, plurals, eventualities, thematic roles, scope, anaphora, presupposition, ellipsis, comparatives, superlatives, tense, aspect, and time-expressions. Hence it will be hard to come up with an annotation scheme unless one permits different level of semantic granularity. The alternative is a theory-neutral black-box type evaluation where we just look at how systems react on various inputs. For this approach, we can consider the well-known task of recognising textual entailment, or the lesser-known task of textual model checking. The disadvantage of black-box methods is that it is difficult to come up with natural data that cover specific semantic phenomena.</abstract>
<identifier type="citekey">bos-2008-lets</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/721_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Let’s not Argue about Semantics
%A Bos, Johan
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F bos-2008-lets
%X Whats the best way to assess the performance of a semantic component in an NLP system? Tradition in NLP evaluation tells us that comparing output against a gold standard is a good idea. To define a gold standard, one first needs to decide on the representation language, and in many cases a first-order language seems a good compromise between expressive power and efficiency. Secondly, one needs to decide how to represent the various semantic phenomena, in particular the depth of analysis of quantification, plurals, eventualities, thematic roles, scope, anaphora, presupposition, ellipsis, comparatives, superlatives, tense, aspect, and time-expressions. Hence it will be hard to come up with an annotation scheme unless one permits different level of semantic granularity. The alternative is a theory-neutral black-box type evaluation where we just look at how systems react on various inputs. For this approach, we can consider the well-known task of recognising textual entailment, or the lesser-known task of textual model checking. The disadvantage of black-box methods is that it is difficult to come up with natural data that cover specific semantic phenomena.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/721_paper.pdf
Markdown (Informal)
[Let’s not Argue about Semantics](http://www.lrec-conf.org/proceedings/lrec2008/pdf/721_paper.pdf) (Bos, LREC 2008)
ACL
- Johan Bos. 2008. Let’s not Argue about Semantics. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).