@inproceedings{varges-etal-2012-semscribe,
title = "{S}em{S}cribe: Natural Language Generation for Medical Reports",
author = "Varges, Sebastian and
Bieler, Heike and
Stede, Manfred and
Faulstich, Lukas C. and
Irsig, Kristin and
Atalla, Malik",
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/165_Paper.pdf",
pages = "2674--2681",
abstract = "Natural language generation in the medical domain is heavily influenced by domain knowledge and genre-specific text characteristics. We present SemScribe, an implemented natural language generation system that produces doctor's letters, in particular descriptions of cardiological findings. Texts in this domain are characterized by a high density of information and a relatively telegraphic style. Domain knowledge is encoded in a medical ontology of about 80,000 concepts. The ontology is used in particular for concept generalizations during referring expression generation. Architecturally, the system is a generation pipeline that uses a corpus-informed syntactic frame approach for realizing sentences appropriate to the domain. The system reads XML documents conforming to the HL7 Clinical Document Architecture (CDA) Standard and enhances them with generated text and references to the used data elements. We conducted a first clinical trial evaluation with medical staff and report on the findings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="varges-etal-2012-semscribe">
<titleInfo>
<title>SemScribe: Natural Language Generation for Medical Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Varges</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heike</namePart>
<namePart type="family">Bieler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manfred</namePart>
<namePart type="family">Stede</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lukas</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Faulstich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristin</namePart>
<namePart type="family">Irsig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malik</namePart>
<namePart type="family">Atalla</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>Natural language generation in the medical domain is heavily influenced by domain knowledge and genre-specific text characteristics. We present SemScribe, an implemented natural language generation system that produces doctor’s letters, in particular descriptions of cardiological findings. Texts in this domain are characterized by a high density of information and a relatively telegraphic style. Domain knowledge is encoded in a medical ontology of about 80,000 concepts. The ontology is used in particular for concept generalizations during referring expression generation. Architecturally, the system is a generation pipeline that uses a corpus-informed syntactic frame approach for realizing sentences appropriate to the domain. The system reads XML documents conforming to the HL7 Clinical Document Architecture (CDA) Standard and enhances them with generated text and references to the used data elements. We conducted a first clinical trial evaluation with medical staff and report on the findings.</abstract>
<identifier type="citekey">varges-etal-2012-semscribe</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/165_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2674</start>
<end>2681</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SemScribe: Natural Language Generation for Medical Reports
%A Varges, Sebastian
%A Bieler, Heike
%A Stede, Manfred
%A Faulstich, Lukas C.
%A Irsig, Kristin
%A Atalla, Malik
%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 varges-etal-2012-semscribe
%X Natural language generation in the medical domain is heavily influenced by domain knowledge and genre-specific text characteristics. We present SemScribe, an implemented natural language generation system that produces doctor’s letters, in particular descriptions of cardiological findings. Texts in this domain are characterized by a high density of information and a relatively telegraphic style. Domain knowledge is encoded in a medical ontology of about 80,000 concepts. The ontology is used in particular for concept generalizations during referring expression generation. Architecturally, the system is a generation pipeline that uses a corpus-informed syntactic frame approach for realizing sentences appropriate to the domain. The system reads XML documents conforming to the HL7 Clinical Document Architecture (CDA) Standard and enhances them with generated text and references to the used data elements. We conducted a first clinical trial evaluation with medical staff and report on the findings.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/165_Paper.pdf
%P 2674-2681
Markdown (Informal)
[SemScribe: Natural Language Generation for Medical Reports](http://www.lrec-conf.org/proceedings/lrec2012/pdf/165_Paper.pdf) (Varges et al., LREC 2012)
ACL
- Sebastian Varges, Heike Bieler, Manfred Stede, Lukas C. Faulstich, Kristin Irsig, and Malik Atalla. 2012. SemScribe: Natural Language Generation for Medical Reports. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2674–2681, Istanbul, Turkey. European Language Resources Association (ELRA).