@inproceedings{kalyan-sangeetha-2020-social,
title = "Social Media Medical Concept Normalization using {R}o{BERT}a in Ontology Enriched Text Similarity Framework",
author = "Kalyan, Katikapalli Subramanyam and
Sangeetha, Sivanesan",
editor = "Shalom, Oren Sar and
Panchenko, Alexander and
dos Santos, Cicero and
Logacheva, Varvara and
Moschitti, Alessandro and
Dagan, Ido",
booktitle = "Proceedings of Knowledgeable NLP: the First Workshop on Integrating Structured Knowledge and Neural Networks for NLP",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.knlp-1.3/",
doi = "10.18653/v1/2020.knlp-1.3",
pages = "21--26",
abstract = "Pattisapu et al. (2020) formulate medical concept normalization (MCN) as text similarity problem and propose a model based on RoBERTa and graph embedding based target concept vectors. However, graph embedding techniques ignore valuable information available in the clinical ontology like concept description and synonyms. In this work, we enhance the model of Pattisapu et al. (2020) with two novel changes. First, we use retrofitted target concept vectors instead of graph embedding based vectors. It is the first work to leverage both concept description and synonyms to represent concepts in the form of retrofitted target concept vectors in text similarity framework based social media MCN. Second, we generate both concept and concept mention vectors with same size which eliminates the need of dense layers to project concept mention vectors into the target concept embedding space. Our model outperforms existing methods with improvements up to 3.75{\%} on two standard datasets. Further when trained only on mapping lexicon synonyms, our model outperforms existing methods with significant improvements up to 14.61{\%}. We attribute these significant improvements to the two novel changes introduced."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kalyan-sangeetha-2020-social">
<titleInfo>
<title>Social Media Medical Concept Normalization using RoBERTa in Ontology Enriched Text Similarity Framework</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>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Knowledgeable NLP: the First Workshop on Integrating Structured Knowledge and Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oren</namePart>
<namePart type="given">Sar</namePart>
<namePart type="family">Shalom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Panchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cicero</namePart>
<namePart type="family">dos Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Moschitti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ido</namePart>
<namePart type="family">Dagan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pattisapu et al. (2020) formulate medical concept normalization (MCN) as text similarity problem and propose a model based on RoBERTa and graph embedding based target concept vectors. However, graph embedding techniques ignore valuable information available in the clinical ontology like concept description and synonyms. In this work, we enhance the model of Pattisapu et al. (2020) with two novel changes. First, we use retrofitted target concept vectors instead of graph embedding based vectors. It is the first work to leverage both concept description and synonyms to represent concepts in the form of retrofitted target concept vectors in text similarity framework based social media MCN. Second, we generate both concept and concept mention vectors with same size which eliminates the need of dense layers to project concept mention vectors into the target concept embedding space. Our model outperforms existing methods with improvements up to 3.75% on two standard datasets. Further when trained only on mapping lexicon synonyms, our model outperforms existing methods with significant improvements up to 14.61%. We attribute these significant improvements to the two novel changes introduced.</abstract>
<identifier type="citekey">kalyan-sangeetha-2020-social</identifier>
<identifier type="doi">10.18653/v1/2020.knlp-1.3</identifier>
<location>
<url>https://aclanthology.org/2020.knlp-1.3/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>21</start>
<end>26</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Social Media Medical Concept Normalization using RoBERTa in Ontology Enriched Text Similarity Framework
%A Kalyan, Katikapalli Subramanyam
%A Sangeetha, Sivanesan
%Y Shalom, Oren Sar
%Y Panchenko, Alexander
%Y dos Santos, Cicero
%Y Logacheva, Varvara
%Y Moschitti, Alessandro
%Y Dagan, Ido
%S Proceedings of Knowledgeable NLP: the First Workshop on Integrating Structured Knowledge and Neural Networks for NLP
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F kalyan-sangeetha-2020-social
%X Pattisapu et al. (2020) formulate medical concept normalization (MCN) as text similarity problem and propose a model based on RoBERTa and graph embedding based target concept vectors. However, graph embedding techniques ignore valuable information available in the clinical ontology like concept description and synonyms. In this work, we enhance the model of Pattisapu et al. (2020) with two novel changes. First, we use retrofitted target concept vectors instead of graph embedding based vectors. It is the first work to leverage both concept description and synonyms to represent concepts in the form of retrofitted target concept vectors in text similarity framework based social media MCN. Second, we generate both concept and concept mention vectors with same size which eliminates the need of dense layers to project concept mention vectors into the target concept embedding space. Our model outperforms existing methods with improvements up to 3.75% on two standard datasets. Further when trained only on mapping lexicon synonyms, our model outperforms existing methods with significant improvements up to 14.61%. We attribute these significant improvements to the two novel changes introduced.
%R 10.18653/v1/2020.knlp-1.3
%U https://aclanthology.org/2020.knlp-1.3/
%U https://doi.org/10.18653/v1/2020.knlp-1.3
%P 21-26
Markdown (Informal)
[Social Media Medical Concept Normalization using RoBERTa in Ontology Enriched Text Similarity Framework](https://aclanthology.org/2020.knlp-1.3/) (Kalyan & Sangeetha, knlp 2020)
ACL