@inproceedings{grujicic-etal-2020-self,
title = "Self-supervised context-aware {COVID-19} document exploration through atlas grounding",
author = "Grujicic, Dusan and
Radevski, Gorjan and
Tuytelaars, Tinne and
Blaschko, Matthew",
booktitle = "Proceedings of the 1st Workshop on {NLP} for {COVID-19} at {ACL} 2020",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlpcovid19-acl.5",
abstract = "In this paper, we aim to develop a self-supervised grounding of Covid-related medical text based on the actual spatial relationships between the referred anatomical concepts. More specifically, we learn to project sentences into a physical space defined by a three-dimensional anatomical atlas, allowing for a visual approach to navigating Covid-related literature. We design a straightforward and empirically effective training objective to reduce the curated data dependency issue. We use BERT as the main building block of our model and perform a quantitative analysis that demonstrates that the model learns a context-aware mapping. We illustrate two potential use-cases for our approach, one in interactive, 3D data exploration, and the other in document retrieval. To accelerate research in this direction, we make public all trained models, codebase and the developed tools, which can be accessed at https://github.com/gorjanradevski/macchina/.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grujicic-etal-2020-self">
<titleInfo>
<title>Self-supervised context-aware COVID-19 document exploration through atlas grounding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dusan</namePart>
<namePart type="family">Grujicic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gorjan</namePart>
<namePart type="family">Radevski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tinne</namePart>
<namePart type="family">Tuytelaars</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Blaschko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-jul</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we aim to develop a self-supervised grounding of Covid-related medical text based on the actual spatial relationships between the referred anatomical concepts. More specifically, we learn to project sentences into a physical space defined by a three-dimensional anatomical atlas, allowing for a visual approach to navigating Covid-related literature. We design a straightforward and empirically effective training objective to reduce the curated data dependency issue. We use BERT as the main building block of our model and perform a quantitative analysis that demonstrates that the model learns a context-aware mapping. We illustrate two potential use-cases for our approach, one in interactive, 3D data exploration, and the other in document retrieval. To accelerate research in this direction, we make public all trained models, codebase and the developed tools, which can be accessed at https://github.com/gorjanradevski/macchina/.</abstract>
<identifier type="citekey">grujicic-etal-2020-self</identifier>
<location>
<url>https://aclanthology.org/2020.nlpcovid19-acl.5</url>
</location>
<part>
<date>2020-jul</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-supervised context-aware COVID-19 document exploration through atlas grounding
%A Grujicic, Dusan
%A Radevski, Gorjan
%A Tuytelaars, Tinne
%A Blaschko, Matthew
%S Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020
%D 2020
%8 jul
%I Association for Computational Linguistics
%C Online
%F grujicic-etal-2020-self
%X In this paper, we aim to develop a self-supervised grounding of Covid-related medical text based on the actual spatial relationships between the referred anatomical concepts. More specifically, we learn to project sentences into a physical space defined by a three-dimensional anatomical atlas, allowing for a visual approach to navigating Covid-related literature. We design a straightforward and empirically effective training objective to reduce the curated data dependency issue. We use BERT as the main building block of our model and perform a quantitative analysis that demonstrates that the model learns a context-aware mapping. We illustrate two potential use-cases for our approach, one in interactive, 3D data exploration, and the other in document retrieval. To accelerate research in this direction, we make public all trained models, codebase and the developed tools, which can be accessed at https://github.com/gorjanradevski/macchina/.
%U https://aclanthology.org/2020.nlpcovid19-acl.5
Markdown (Informal)
[Self-supervised context-aware COVID-19 document exploration through atlas grounding](https://aclanthology.org/2020.nlpcovid19-acl.5) (Grujicic et al., NLP-COVID19 2020)
ACL