@inproceedings{datta-etal-2022-cross,
title = "A Cross-document Coreference Dataset for Longitudinal Tracking across Radiology Reports",
author = "Datta, Surabhi and
Lam, Hio Cheng and
Pajouhi, Atieh and
Mogalla, Sunitha and
Roberts, Kirk",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.393",
pages = "3686--3695",
abstract = "This paper proposes a new cross-document coreference resolution (CDCR) dataset for identifying co-referring radiological findings and medical devices across a patient{'}s radiology reports. Our annotated corpus contains 5872 mentions (findings and devices) spanning 638 MIMIC-III radiology reports across 60 patients, covering multiple imaging modalities and anatomies. There are a total of 2292 mention chains. We describe the annotation process in detail, highlighting the complexities involved in creating a sizable and realistic dataset for radiology CDCR. We apply two baseline methods{--}string matching and transformer language models (BERT){--}to identify cross-report coreferences. Our results indicate the requirement of further model development targeting better understanding of domain language and context to address this challenging and unexplored task. This dataset can serve as a resource to develop more advanced natural language processing CDCR methods in the future. This is one of the first attempts focusing on CDCR in the clinical domain and holds potential in benefiting physicians and clinical research through long-term tracking of radiology findings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="datta-etal-2022-cross">
<titleInfo>
<title>A Cross-document Coreference Dataset for Longitudinal Tracking across Radiology Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Surabhi</namePart>
<namePart type="family">Datta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hio</namePart>
<namePart type="given">Cheng</namePart>
<namePart type="family">Lam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atieh</namePart>
<namePart type="family">Pajouhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunitha</namePart>
<namePart type="family">Mogalla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper proposes a new cross-document coreference resolution (CDCR) dataset for identifying co-referring radiological findings and medical devices across a patient’s radiology reports. Our annotated corpus contains 5872 mentions (findings and devices) spanning 638 MIMIC-III radiology reports across 60 patients, covering multiple imaging modalities and anatomies. There are a total of 2292 mention chains. We describe the annotation process in detail, highlighting the complexities involved in creating a sizable and realistic dataset for radiology CDCR. We apply two baseline methods–string matching and transformer language models (BERT)–to identify cross-report coreferences. Our results indicate the requirement of further model development targeting better understanding of domain language and context to address this challenging and unexplored task. This dataset can serve as a resource to develop more advanced natural language processing CDCR methods in the future. This is one of the first attempts focusing on CDCR in the clinical domain and holds potential in benefiting physicians and clinical research through long-term tracking of radiology findings.</abstract>
<identifier type="citekey">datta-etal-2022-cross</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.393</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3686</start>
<end>3695</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Cross-document Coreference Dataset for Longitudinal Tracking across Radiology Reports
%A Datta, Surabhi
%A Lam, Hio Cheng
%A Pajouhi, Atieh
%A Mogalla, Sunitha
%A Roberts, Kirk
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F datta-etal-2022-cross
%X This paper proposes a new cross-document coreference resolution (CDCR) dataset for identifying co-referring radiological findings and medical devices across a patient’s radiology reports. Our annotated corpus contains 5872 mentions (findings and devices) spanning 638 MIMIC-III radiology reports across 60 patients, covering multiple imaging modalities and anatomies. There are a total of 2292 mention chains. We describe the annotation process in detail, highlighting the complexities involved in creating a sizable and realistic dataset for radiology CDCR. We apply two baseline methods–string matching and transformer language models (BERT)–to identify cross-report coreferences. Our results indicate the requirement of further model development targeting better understanding of domain language and context to address this challenging and unexplored task. This dataset can serve as a resource to develop more advanced natural language processing CDCR methods in the future. This is one of the first attempts focusing on CDCR in the clinical domain and holds potential in benefiting physicians and clinical research through long-term tracking of radiology findings.
%U https://aclanthology.org/2022.lrec-1.393
%P 3686-3695
Markdown (Informal)
[A Cross-document Coreference Dataset for Longitudinal Tracking across Radiology Reports](https://aclanthology.org/2022.lrec-1.393) (Datta et al., LREC 2022)
ACL