@inproceedings{loukachevitch-etal-2024-biomedical,
title = "Biomedical Concept Normalization over Nested Entities with Partial {UMLS} Terminology in {R}ussian",
author = "Loukachevitch, Natalia and
Sakhovskiy, Andrey and
Tutubalina, Elena",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.213/",
pages = "2383--2389",
abstract = "We present a new manually annotated dataset of PubMed abstracts for concept normalization in Russian. It contains over 23,641 entity mentions in 756 documents linked to 4,544 unique concepts from the UMLS ontology. Compared to existing corpora, we explore two novel annotation characteristics: the nestedness of named entities and the incompleteness of the Russian medical terminology in UMLS. 4,424 entity mentions are linked to 1,535 unique English concepts absent in the Russian part of the UMLS ontology. We present several baselines for normalization over nested named entities obtained with state-of-the-art models such as SapBERT. Our experimental results show that models pre-trained on graph structural data from UMLS achieve superior performance in a zero-shot setting on bilingual terminology."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="loukachevitch-etal-2024-biomedical">
<titleInfo>
<title>Biomedical Concept Normalization over Nested Entities with Partial UMLS Terminology in Russian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Loukachevitch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Sakhovskiy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Tutubalina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a new manually annotated dataset of PubMed abstracts for concept normalization in Russian. It contains over 23,641 entity mentions in 756 documents linked to 4,544 unique concepts from the UMLS ontology. Compared to existing corpora, we explore two novel annotation characteristics: the nestedness of named entities and the incompleteness of the Russian medical terminology in UMLS. 4,424 entity mentions are linked to 1,535 unique English concepts absent in the Russian part of the UMLS ontology. We present several baselines for normalization over nested named entities obtained with state-of-the-art models such as SapBERT. Our experimental results show that models pre-trained on graph structural data from UMLS achieve superior performance in a zero-shot setting on bilingual terminology.</abstract>
<identifier type="citekey">loukachevitch-etal-2024-biomedical</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.213/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>2383</start>
<end>2389</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Biomedical Concept Normalization over Nested Entities with Partial UMLS Terminology in Russian
%A Loukachevitch, Natalia
%A Sakhovskiy, Andrey
%A Tutubalina, Elena
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F loukachevitch-etal-2024-biomedical
%X We present a new manually annotated dataset of PubMed abstracts for concept normalization in Russian. It contains over 23,641 entity mentions in 756 documents linked to 4,544 unique concepts from the UMLS ontology. Compared to existing corpora, we explore two novel annotation characteristics: the nestedness of named entities and the incompleteness of the Russian medical terminology in UMLS. 4,424 entity mentions are linked to 1,535 unique English concepts absent in the Russian part of the UMLS ontology. We present several baselines for normalization over nested named entities obtained with state-of-the-art models such as SapBERT. Our experimental results show that models pre-trained on graph structural data from UMLS achieve superior performance in a zero-shot setting on bilingual terminology.
%U https://aclanthology.org/2024.lrec-main.213/
%P 2383-2389
Markdown (Informal)
[Biomedical Concept Normalization over Nested Entities with Partial UMLS Terminology in Russian](https://aclanthology.org/2024.lrec-main.213/) (Loukachevitch et al., LREC-COLING 2024)
ACL