@inproceedings{nejadgholi-etal-2019-recognizing,
title = "Recognizing {UMLS} Semantic Types with Deep Learning",
author = "Nejadgholi, Isar and
Fraser, Kathleen C. and
De Bruijn, Berry and
Li, Muqun and
LaPlante, Astha and
Zine El Abidine, Khaldoun",
editor = "Holderness, Eben and
Jimeno Yepes, Antonio and
Lavelli, Alberto and
Minard, Anne-Lyse and
Pustejovsky, James and
Rinaldi, Fabio",
booktitle = "Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)",
month = nov,
year = "2019",
address = "Hong Kong",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6219",
doi = "10.18653/v1/D19-6219",
pages = "157--167",
abstract = "Entity recognition is a critical first step to a number of clinical NLP applications, such as entity linking and relation extraction. We present the first attempt to apply state-of-the-art entity recognition approaches on a newly released dataset, MedMentions. This dataset contains over 4000 biomedical abstracts, annotated for UMLS semantic types. In comparison to existing datasets, MedMentions contains a far greater number of entity types, and thus represents a more challenging but realistic scenario in a real-world setting. We explore a number of relevant dimensions, including the use of contextual versus non-contextual word embeddings, general versus domain-specific unsupervised pre-training, and different deep learning architectures. We contrast our results against the well-known i2b2 2010 entity recognition dataset, and propose a new method to combine general and domain-specific information. While producing a state-of-the-art result for the i2b2 2010 task (F1 = 0.90), our results on MedMentions are significantly lower (F1 = 0.63), suggesting there is still plenty of opportunity for improvement on this new data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nejadgholi-etal-2019-recognizing">
<titleInfo>
<title>Recognizing UMLS Semantic Types with Deep Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isar</namePart>
<namePart type="family">Nejadgholi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathleen</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berry</namePart>
<namePart type="family">De Bruijn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muqun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Astha</namePart>
<namePart type="family">LaPlante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khaldoun</namePart>
<namePart type="family">Zine El Abidine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)</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">Hong Kong</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Entity recognition is a critical first step to a number of clinical NLP applications, such as entity linking and relation extraction. We present the first attempt to apply state-of-the-art entity recognition approaches on a newly released dataset, MedMentions. This dataset contains over 4000 biomedical abstracts, annotated for UMLS semantic types. In comparison to existing datasets, MedMentions contains a far greater number of entity types, and thus represents a more challenging but realistic scenario in a real-world setting. We explore a number of relevant dimensions, including the use of contextual versus non-contextual word embeddings, general versus domain-specific unsupervised pre-training, and different deep learning architectures. We contrast our results against the well-known i2b2 2010 entity recognition dataset, and propose a new method to combine general and domain-specific information. While producing a state-of-the-art result for the i2b2 2010 task (F1 = 0.90), our results on MedMentions are significantly lower (F1 = 0.63), suggesting there is still plenty of opportunity for improvement on this new data.</abstract>
<identifier type="citekey">nejadgholi-etal-2019-recognizing</identifier>
<identifier type="doi">10.18653/v1/D19-6219</identifier>
<location>
<url>https://aclanthology.org/D19-6219</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>157</start>
<end>167</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recognizing UMLS Semantic Types with Deep Learning
%A Nejadgholi, Isar
%A Fraser, Kathleen C.
%A De Bruijn, Berry
%A Li, Muqun
%A LaPlante, Astha
%A Zine El Abidine, Khaldoun
%Y Holderness, Eben
%Y Jimeno Yepes, Antonio
%Y Lavelli, Alberto
%Y Minard, Anne-Lyse
%Y Pustejovsky, James
%Y Rinaldi, Fabio
%S Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong
%F nejadgholi-etal-2019-recognizing
%X Entity recognition is a critical first step to a number of clinical NLP applications, such as entity linking and relation extraction. We present the first attempt to apply state-of-the-art entity recognition approaches on a newly released dataset, MedMentions. This dataset contains over 4000 biomedical abstracts, annotated for UMLS semantic types. In comparison to existing datasets, MedMentions contains a far greater number of entity types, and thus represents a more challenging but realistic scenario in a real-world setting. We explore a number of relevant dimensions, including the use of contextual versus non-contextual word embeddings, general versus domain-specific unsupervised pre-training, and different deep learning architectures. We contrast our results against the well-known i2b2 2010 entity recognition dataset, and propose a new method to combine general and domain-specific information. While producing a state-of-the-art result for the i2b2 2010 task (F1 = 0.90), our results on MedMentions are significantly lower (F1 = 0.63), suggesting there is still plenty of opportunity for improvement on this new data.
%R 10.18653/v1/D19-6219
%U https://aclanthology.org/D19-6219
%U https://doi.org/10.18653/v1/D19-6219
%P 157-167
Markdown (Informal)
[Recognizing UMLS Semantic Types with Deep Learning](https://aclanthology.org/D19-6219) (Nejadgholi et al., Louhi 2019)
ACL
- Isar Nejadgholi, Kathleen C. Fraser, Berry De Bruijn, Muqun Li, Astha LaPlante, and Khaldoun Zine El Abidine. 2019. Recognizing UMLS Semantic Types with Deep Learning. In Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019), pages 157–167, Hong Kong. Association for Computational Linguistics.