@inproceedings{raghavan-etal-2021-emrkbqa,
title = "emr{KBQA}: A Clinical Knowledge-Base Question Answering Dataset",
author = "Raghavan, Preethi and
Liang, Jennifer J and
Mahajan, Diwakar and
Chandra, Rachita and
Szolovits, Peter",
booktitle = "Proceedings of the 20th Workshop on Biomedical Language Processing",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.bionlp-1.7",
doi = "10.18653/v1/2021.bionlp-1.7",
pages = "64--73",
abstract = "We present emrKBQA, a dataset for answering physician questions from a structured patient record. It consists of questions, logical forms and answers. The questions and logical forms are generated based on real-world physician questions and are slot-filled and answered from patients in the MIMIC-III KB through a semi-automated process. This community-shared release consists of over 940000 question, logical form and answer triplets with 389 types of questions and {\textasciitilde}7.5 paraphrases per question type. We perform experiments to validate the quality of the dataset and set benchmarks for question to logical form learning that helps answer questions on this dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="raghavan-etal-2021-emrkbqa">
<titleInfo>
<title>emrKBQA: A Clinical Knowledge-Base Question Answering Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Preethi</namePart>
<namePart type="family">Raghavan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diwakar</namePart>
<namePart type="family">Mahajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachita</namePart>
<namePart type="family">Chandra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Szolovits</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Workshop on Biomedical Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present emrKBQA, a dataset for answering physician questions from a structured patient record. It consists of questions, logical forms and answers. The questions and logical forms are generated based on real-world physician questions and are slot-filled and answered from patients in the MIMIC-III KB through a semi-automated process. This community-shared release consists of over 940000 question, logical form and answer triplets with 389 types of questions and 7.5 paraphrases per question type. We perform experiments to validate the quality of the dataset and set benchmarks for question to logical form learning that helps answer questions on this dataset.</abstract>
<identifier type="citekey">raghavan-etal-2021-emrkbqa</identifier>
<identifier type="doi">10.18653/v1/2021.bionlp-1.7</identifier>
<location>
<url>https://aclanthology.org/2021.bionlp-1.7</url>
</location>
<part>
<date>2021-jun</date>
<extent unit="page">
<start>64</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T emrKBQA: A Clinical Knowledge-Base Question Answering Dataset
%A Raghavan, Preethi
%A Liang, Jennifer J.
%A Mahajan, Diwakar
%A Chandra, Rachita
%A Szolovits, Peter
%S Proceedings of the 20th Workshop on Biomedical Language Processing
%D 2021
%8 jun
%I Association for Computational Linguistics
%C Online
%F raghavan-etal-2021-emrkbqa
%X We present emrKBQA, a dataset for answering physician questions from a structured patient record. It consists of questions, logical forms and answers. The questions and logical forms are generated based on real-world physician questions and are slot-filled and answered from patients in the MIMIC-III KB through a semi-automated process. This community-shared release consists of over 940000 question, logical form and answer triplets with 389 types of questions and 7.5 paraphrases per question type. We perform experiments to validate the quality of the dataset and set benchmarks for question to logical form learning that helps answer questions on this dataset.
%R 10.18653/v1/2021.bionlp-1.7
%U https://aclanthology.org/2021.bionlp-1.7
%U https://doi.org/10.18653/v1/2021.bionlp-1.7
%P 64-73
Markdown (Informal)
[emrKBQA: A Clinical Knowledge-Base Question Answering Dataset](https://aclanthology.org/2021.bionlp-1.7) (Raghavan et al., BioNLP 2021)
ACL