@inproceedings{wang-etal-2018-learning-better,
title = "On Learning Better Embeddings from {C}hinese Clinical Records: Study on Combining In-Domain and Out-Domain Data",
author = "Wang, Yaqiang and
Chen, Yunhui and
Shu, Hongping and
Jiang, Yongguang",
editor = "Demner-Fushman, Dina and
Cohen, Kevin Bretonnel and
Ananiadou, Sophia and
Tsujii, Junichi",
booktitle = "Proceedings of the {B}io{NLP} 2018 workshop",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-2323",
doi = "10.18653/v1/W18-2323",
pages = "177--182",
abstract = "High quality word embeddings are of great significance to advance applications of biomedical natural language processing. In recent years, a surge of interest on how to learn good embeddings and evaluate embedding quality based on English medical text has become increasing evident, however a limited number of studies based on Chinese medical text, particularly Chinese clinical records, were performed. Herein, we proposed a novel approach of improving the quality of learned embeddings using out-domain data as a supplementary in the case of limited Chinese clinical records. Moreover, the embedding quality evaluation method was conducted based on Medical Conceptual Similarity Property. The experimental results revealed that selecting good training samples was necessary, and collecting right amount of out-domain data and trading off between the quality of embeddings and the training time consumption were essential factors for better embeddings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2018-learning-better">
<titleInfo>
<title>On Learning Better Embeddings from Chinese Clinical Records: Study on Combining In-Domain and Out-Domain Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaqiang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunhui</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongping</namePart>
<namePart type="family">Shu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongguang</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the BioNLP 2018 workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">Bretonnel</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>High quality word embeddings are of great significance to advance applications of biomedical natural language processing. In recent years, a surge of interest on how to learn good embeddings and evaluate embedding quality based on English medical text has become increasing evident, however a limited number of studies based on Chinese medical text, particularly Chinese clinical records, were performed. Herein, we proposed a novel approach of improving the quality of learned embeddings using out-domain data as a supplementary in the case of limited Chinese clinical records. Moreover, the embedding quality evaluation method was conducted based on Medical Conceptual Similarity Property. The experimental results revealed that selecting good training samples was necessary, and collecting right amount of out-domain data and trading off between the quality of embeddings and the training time consumption were essential factors for better embeddings.</abstract>
<identifier type="citekey">wang-etal-2018-learning-better</identifier>
<identifier type="doi">10.18653/v1/W18-2323</identifier>
<location>
<url>https://aclanthology.org/W18-2323</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>177</start>
<end>182</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Learning Better Embeddings from Chinese Clinical Records: Study on Combining In-Domain and Out-Domain Data
%A Wang, Yaqiang
%A Chen, Yunhui
%A Shu, Hongping
%A Jiang, Yongguang
%Y Demner-Fushman, Dina
%Y Cohen, Kevin Bretonnel
%Y Ananiadou, Sophia
%Y Tsujii, Junichi
%S Proceedings of the BioNLP 2018 workshop
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F wang-etal-2018-learning-better
%X High quality word embeddings are of great significance to advance applications of biomedical natural language processing. In recent years, a surge of interest on how to learn good embeddings and evaluate embedding quality based on English medical text has become increasing evident, however a limited number of studies based on Chinese medical text, particularly Chinese clinical records, were performed. Herein, we proposed a novel approach of improving the quality of learned embeddings using out-domain data as a supplementary in the case of limited Chinese clinical records. Moreover, the embedding quality evaluation method was conducted based on Medical Conceptual Similarity Property. The experimental results revealed that selecting good training samples was necessary, and collecting right amount of out-domain data and trading off between the quality of embeddings and the training time consumption were essential factors for better embeddings.
%R 10.18653/v1/W18-2323
%U https://aclanthology.org/W18-2323
%U https://doi.org/10.18653/v1/W18-2323
%P 177-182
Markdown (Informal)
[On Learning Better Embeddings from Chinese Clinical Records: Study on Combining In-Domain and Out-Domain Data](https://aclanthology.org/W18-2323) (Wang et al., BioNLP 2018)
ACL