@inproceedings{gokcen-etal-2016-corpus,
title = "A Corpus of Word-Aligned Asked and Anticipated Questions in a Virtual Patient Dialogue System",
author = "Gokcen, Ajda and
Jaffe, Evan and
Erdmann, Johnsey and
White, Michael and
Danforth, Douglas",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1506/",
pages = "3174--3179",
abstract = "We present a corpus of virtual patient dialogues to which we have added manually annotated gold standard word alignments. Since each question asked by a medical student in the dialogues is mapped to a canonical, anticipated version of the question, the corpus implicitly defines a large set of paraphrase (and non-paraphrase) pairs. We also present a novel process for selecting the most useful data to annotate with word alignments and for ensuring consistent paraphrase status decisions. In support of this process, we have enhanced the earlier Edinburgh alignment tool (Cohn et al., 2008) and revised and extended the Edinburgh guidelines, in particular adding guidance intended to ensure that the word alignments are consistent with the overall paraphrase status decision. The finished corpus and the enhanced alignment tool are made freely available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gokcen-etal-2016-corpus">
<titleInfo>
<title>A Corpus of Word-Aligned Asked and Anticipated Questions in a Virtual Patient Dialogue System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ajda</namePart>
<namePart type="family">Gokcen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evan</namePart>
<namePart type="family">Jaffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johnsey</namePart>
<namePart type="family">Erdmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">White</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Douglas</namePart>
<namePart type="family">Danforth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a corpus of virtual patient dialogues to which we have added manually annotated gold standard word alignments. Since each question asked by a medical student in the dialogues is mapped to a canonical, anticipated version of the question, the corpus implicitly defines a large set of paraphrase (and non-paraphrase) pairs. We also present a novel process for selecting the most useful data to annotate with word alignments and for ensuring consistent paraphrase status decisions. In support of this process, we have enhanced the earlier Edinburgh alignment tool (Cohn et al., 2008) and revised and extended the Edinburgh guidelines, in particular adding guidance intended to ensure that the word alignments are consistent with the overall paraphrase status decision. The finished corpus and the enhanced alignment tool are made freely available.</abstract>
<identifier type="citekey">gokcen-etal-2016-corpus</identifier>
<location>
<url>https://aclanthology.org/L16-1506/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3174</start>
<end>3179</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Corpus of Word-Aligned Asked and Anticipated Questions in a Virtual Patient Dialogue System
%A Gokcen, Ajda
%A Jaffe, Evan
%A Erdmann, Johnsey
%A White, Michael
%A Danforth, Douglas
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F gokcen-etal-2016-corpus
%X We present a corpus of virtual patient dialogues to which we have added manually annotated gold standard word alignments. Since each question asked by a medical student in the dialogues is mapped to a canonical, anticipated version of the question, the corpus implicitly defines a large set of paraphrase (and non-paraphrase) pairs. We also present a novel process for selecting the most useful data to annotate with word alignments and for ensuring consistent paraphrase status decisions. In support of this process, we have enhanced the earlier Edinburgh alignment tool (Cohn et al., 2008) and revised and extended the Edinburgh guidelines, in particular adding guidance intended to ensure that the word alignments are consistent with the overall paraphrase status decision. The finished corpus and the enhanced alignment tool are made freely available.
%U https://aclanthology.org/L16-1506/
%P 3174-3179
Markdown (Informal)
[A Corpus of Word-Aligned Asked and Anticipated Questions in a Virtual Patient Dialogue System](https://aclanthology.org/L16-1506/) (Gokcen et al., LREC 2016)
ACL