@inproceedings{li-etal-2020-towards,
title = "Towards Medical Machine Reading Comprehension with Structural Knowledge and Plain Text",
author = "Li, Dongfang and
Hu, Baotian and
Chen, Qingcai and
Peng, Weihua and
Wang, Anqi",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.111/",
doi = "10.18653/v1/2020.emnlp-main.111",
pages = "1427--1438",
abstract = "Machine reading comprehension (MRC) has achieved significant progress on the open domain in recent years, mainly due to large-scale pre-trained language models. However, it performs much worse in specific domains such as the medical field due to the lack of extensive training data and professional structural knowledge neglect. As an effort, we first collect a large scale medical multi-choice question dataset (more than 21k instances) for the National Licensed Pharmacist Examination in China. It is a challenging medical examination with a passing rate of less than 14.2{\%} in 2018. Then we propose a novel reading comprehension model KMQA, which can fully exploit the structural medical knowledge (i.e., medical knowledge graph) and the reference medical plain text (i.e., text snippets retrieved from reference books). The experimental results indicate that the KMQA outperforms existing competitive models with a large margin and passes the exam with 61.8{\%} accuracy rate on the test set."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2020-towards">
<titleInfo>
<title>Towards Medical Machine Reading Comprehension with Structural Knowledge and Plain Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongfang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baotian</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingcai</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weihua</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anqi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine reading comprehension (MRC) has achieved significant progress on the open domain in recent years, mainly due to large-scale pre-trained language models. However, it performs much worse in specific domains such as the medical field due to the lack of extensive training data and professional structural knowledge neglect. As an effort, we first collect a large scale medical multi-choice question dataset (more than 21k instances) for the National Licensed Pharmacist Examination in China. It is a challenging medical examination with a passing rate of less than 14.2% in 2018. Then we propose a novel reading comprehension model KMQA, which can fully exploit the structural medical knowledge (i.e., medical knowledge graph) and the reference medical plain text (i.e., text snippets retrieved from reference books). The experimental results indicate that the KMQA outperforms existing competitive models with a large margin and passes the exam with 61.8% accuracy rate on the test set.</abstract>
<identifier type="citekey">li-etal-2020-towards</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.111</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.111/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>1427</start>
<end>1438</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Medical Machine Reading Comprehension with Structural Knowledge and Plain Text
%A Li, Dongfang
%A Hu, Baotian
%A Chen, Qingcai
%A Peng, Weihua
%A Wang, Anqi
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F li-etal-2020-towards
%X Machine reading comprehension (MRC) has achieved significant progress on the open domain in recent years, mainly due to large-scale pre-trained language models. However, it performs much worse in specific domains such as the medical field due to the lack of extensive training data and professional structural knowledge neglect. As an effort, we first collect a large scale medical multi-choice question dataset (more than 21k instances) for the National Licensed Pharmacist Examination in China. It is a challenging medical examination with a passing rate of less than 14.2% in 2018. Then we propose a novel reading comprehension model KMQA, which can fully exploit the structural medical knowledge (i.e., medical knowledge graph) and the reference medical plain text (i.e., text snippets retrieved from reference books). The experimental results indicate that the KMQA outperforms existing competitive models with a large margin and passes the exam with 61.8% accuracy rate on the test set.
%R 10.18653/v1/2020.emnlp-main.111
%U https://aclanthology.org/2020.emnlp-main.111/
%U https://doi.org/10.18653/v1/2020.emnlp-main.111
%P 1427-1438
Markdown (Informal)
[Towards Medical Machine Reading Comprehension with Structural Knowledge and Plain Text](https://aclanthology.org/2020.emnlp-main.111/) (Li et al., EMNLP 2020)
ACL