@inproceedings{jimeno-yepes-verspoor-2022-distinguishing,
title = "Distinguishing between focus and background entities in biomedical corpora using discourse structure and transformers",
author = "Jimeno Yepes, Antonio and
Verspoor, Karin",
editor = "Lavelli, Alberto and
Holderness, Eben and
Jimeno Yepes, Antonio and
Minard, Anne-Lyse and
Pustejovsky, James and
Rinaldi, Fabio",
booktitle = "Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.louhi-1.4",
doi = "10.18653/v1/2022.louhi-1.4",
pages = "35--40",
abstract = "Scientific documents typically contain numerous entity mentions, while only a subset are directly relevant to the key contributions of the paper. Distinguishing these focus entities from background ones effectively could improve the recovery of relevant documents and the extraction of information from documents. To study the identification of focus entities, we developed two large datasets of disease-causing biological pathogens using MEDLINE, the largest collection of biomedical citations, and PubMed Central, a collection of full text articles. The focus entities were identified using human-curated indexing on these collections. Experiments with machine learning methods to identify focus entities show that transformer methods achieve high precision and recall and that document discourse information is relevant. The work lays the foundation for more targeted retrieval/summarisation of entity-relevant documents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jimeno-yepes-verspoor-2022-distinguishing">
<titleInfo>
<title>Distinguishing between focus and background entities in biomedical corpora using discourse structure and transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Jimeno Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karin</namePart>
<namePart type="family">Verspoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)</title>
</titleInfo>
<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">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">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">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Scientific documents typically contain numerous entity mentions, while only a subset are directly relevant to the key contributions of the paper. Distinguishing these focus entities from background ones effectively could improve the recovery of relevant documents and the extraction of information from documents. To study the identification of focus entities, we developed two large datasets of disease-causing biological pathogens using MEDLINE, the largest collection of biomedical citations, and PubMed Central, a collection of full text articles. The focus entities were identified using human-curated indexing on these collections. Experiments with machine learning methods to identify focus entities show that transformer methods achieve high precision and recall and that document discourse information is relevant. The work lays the foundation for more targeted retrieval/summarisation of entity-relevant documents.</abstract>
<identifier type="citekey">jimeno-yepes-verspoor-2022-distinguishing</identifier>
<identifier type="doi">10.18653/v1/2022.louhi-1.4</identifier>
<location>
<url>https://aclanthology.org/2022.louhi-1.4</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>35</start>
<end>40</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Distinguishing between focus and background entities in biomedical corpora using discourse structure and transformers
%A Jimeno Yepes, Antonio
%A Verspoor, Karin
%Y Lavelli, Alberto
%Y Holderness, Eben
%Y Jimeno Yepes, Antonio
%Y Minard, Anne-Lyse
%Y Pustejovsky, James
%Y Rinaldi, Fabio
%S Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F jimeno-yepes-verspoor-2022-distinguishing
%X Scientific documents typically contain numerous entity mentions, while only a subset are directly relevant to the key contributions of the paper. Distinguishing these focus entities from background ones effectively could improve the recovery of relevant documents and the extraction of information from documents. To study the identification of focus entities, we developed two large datasets of disease-causing biological pathogens using MEDLINE, the largest collection of biomedical citations, and PubMed Central, a collection of full text articles. The focus entities were identified using human-curated indexing on these collections. Experiments with machine learning methods to identify focus entities show that transformer methods achieve high precision and recall and that document discourse information is relevant. The work lays the foundation for more targeted retrieval/summarisation of entity-relevant documents.
%R 10.18653/v1/2022.louhi-1.4
%U https://aclanthology.org/2022.louhi-1.4
%U https://doi.org/10.18653/v1/2022.louhi-1.4
%P 35-40
Markdown (Informal)
[Distinguishing between focus and background entities in biomedical corpora using discourse structure and transformers](https://aclanthology.org/2022.louhi-1.4) (Jimeno Yepes & Verspoor, Louhi 2022)
ACL