@inproceedings{kalyan-sangeetha-2020-medical,
title = "Medical Concept Normalization in User-Generated Texts by Learning Target Concept Embeddings",
author = "Kalyan, Katikapalli Subramanyam and
Sangeetha, Sivanesan",
editor = "Holderness, Eben and
Jimeno Yepes, Antonio and
Lavelli, Alberto and
Minard, Anne-Lyse and
Pustejovsky, James and
Rinaldi, Fabio",
booktitle = "Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.louhi-1.3/",
doi = "10.18653/v1/2020.louhi-1.3",
pages = "18--23",
abstract = "Medical concept normalization helps in discovering standard concepts in free-form text i.e., maps health-related mentions to standard concepts in a clinical knowledge base. It is much beyond simple string matching and requires a deep semantic understanding of concept mentions. Recent research approach concept normalization as either text classification or text similarity. The main drawback in existing a) text classification approach is ignoring valuable target concepts information in learning input concept mention representation b) text similarity approach is the need to separately generate target concept embeddings which is time and resource consuming. Our proposed model overcomes these drawbacks by jointly learning the representations of input concept mention and target concepts. First, we learn input concept mention representation using RoBERTa. Second, we find cosine similarity between embeddings of input concept mention and all the target concepts. Here, embeddings of target concepts are randomly initialized and then updated during training. Finally, the target concept with maximum cosine similarity is assigned to the input concept mention. Our model surpasses all the existing methods across three standard datasets by improving accuracy up to 2.31{\%}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kalyan-sangeetha-2020-medical">
<titleInfo>
<title>Medical Concept Normalization in User-Generated Texts by Learning Target Concept Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katikapalli</namePart>
<namePart type="given">Subramanyam</namePart>
<namePart type="family">Kalyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sivanesan</namePart>
<namePart type="family">Sangeetha</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 11th International Workshop on Health Text Mining and Information Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eben</namePart>
<namePart type="family">Holderness</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Jimeno Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Lavelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Lyse</namePart>
<namePart type="family">Minard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</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>Medical concept normalization helps in discovering standard concepts in free-form text i.e., maps health-related mentions to standard concepts in a clinical knowledge base. It is much beyond simple string matching and requires a deep semantic understanding of concept mentions. Recent research approach concept normalization as either text classification or text similarity. The main drawback in existing a) text classification approach is ignoring valuable target concepts information in learning input concept mention representation b) text similarity approach is the need to separately generate target concept embeddings which is time and resource consuming. Our proposed model overcomes these drawbacks by jointly learning the representations of input concept mention and target concepts. First, we learn input concept mention representation using RoBERTa. Second, we find cosine similarity between embeddings of input concept mention and all the target concepts. Here, embeddings of target concepts are randomly initialized and then updated during training. Finally, the target concept with maximum cosine similarity is assigned to the input concept mention. Our model surpasses all the existing methods across three standard datasets by improving accuracy up to 2.31%.</abstract>
<identifier type="citekey">kalyan-sangeetha-2020-medical</identifier>
<identifier type="doi">10.18653/v1/2020.louhi-1.3</identifier>
<location>
<url>https://aclanthology.org/2020.louhi-1.3/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>18</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Medical Concept Normalization in User-Generated Texts by Learning Target Concept Embeddings
%A Kalyan, Katikapalli Subramanyam
%A Sangeetha, Sivanesan
%Y Holderness, Eben
%Y Jimeno Yepes, Antonio
%Y Lavelli, Alberto
%Y Minard, Anne-Lyse
%Y Pustejovsky, James
%Y Rinaldi, Fabio
%S Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F kalyan-sangeetha-2020-medical
%X Medical concept normalization helps in discovering standard concepts in free-form text i.e., maps health-related mentions to standard concepts in a clinical knowledge base. It is much beyond simple string matching and requires a deep semantic understanding of concept mentions. Recent research approach concept normalization as either text classification or text similarity. The main drawback in existing a) text classification approach is ignoring valuable target concepts information in learning input concept mention representation b) text similarity approach is the need to separately generate target concept embeddings which is time and resource consuming. Our proposed model overcomes these drawbacks by jointly learning the representations of input concept mention and target concepts. First, we learn input concept mention representation using RoBERTa. Second, we find cosine similarity between embeddings of input concept mention and all the target concepts. Here, embeddings of target concepts are randomly initialized and then updated during training. Finally, the target concept with maximum cosine similarity is assigned to the input concept mention. Our model surpasses all the existing methods across three standard datasets by improving accuracy up to 2.31%.
%R 10.18653/v1/2020.louhi-1.3
%U https://aclanthology.org/2020.louhi-1.3/
%U https://doi.org/10.18653/v1/2020.louhi-1.3
%P 18-23
Markdown (Informal)
[Medical Concept Normalization in User-Generated Texts by Learning Target Concept Embeddings](https://aclanthology.org/2020.louhi-1.3/) (Kalyan & Sangeetha, Louhi 2020)
ACL