@inproceedings{basu-etal-2020-erlkg,
title = "{ERLKG}: Entity Representation Learning and Knowledge Graph based association analysis of {COVID}-19 through mining of unstructured biomedical corpora",
author = "Basu, Sayantan and
Chakraborty, Sinchani and
Hassan, Atif and
Siddique, Sana and
Anand, Ashish",
booktitle = "Proceedings of the First Workshop on Scholarly Document Processing",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.sdp-1.15",
doi = "10.18653/v1/2020.sdp-1.15",
pages = "127--137",
abstract = "We introduce a generic, human-out-of-the-loop pipeline, ERLKG, to perform rapid association analysis of any biomedical entity with other existing entities from a corpora of the same domain. Our pipeline consists of a Knowledge Graph (KG) created from the Open Source CORD-19 dataset by fully automating the procedure of information extraction using SciBERT. The best latent entity representations are then found by benchnmarking different KG embedding techniques on the task of link prediction using a Graph Convolution Network Auto Encoder (GCN-AE). We demonstrate the utility of ERLKG with respect to COVID-19 through multiple qualitative evaluations. Due to the lack of a gold standard, we propose a relatively large intrinsic evaluation dataset for COVID-19 and use it for validating the top two performing KG embedding techniques. We find TransD to be the best performing KG embedding technique with Pearson and Spearman correlation scores of 0.4348 and 0.4570 respectively. We demonstrate that a considerable number of ERLKG{'}s top protein, chemical and disease predictions are currently in consideration for COVID-19 related research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="basu-etal-2020-erlkg">
<titleInfo>
<title>ERLKG: Entity Representation Learning and Knowledge Graph based association analysis of COVID-19 through mining of unstructured biomedical corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sayantan</namePart>
<namePart type="family">Basu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sinchani</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atif</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sana</namePart>
<namePart type="family">Siddique</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashish</namePart>
<namePart type="family">Anand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Scholarly Document Processing</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>We introduce a generic, human-out-of-the-loop pipeline, ERLKG, to perform rapid association analysis of any biomedical entity with other existing entities from a corpora of the same domain. Our pipeline consists of a Knowledge Graph (KG) created from the Open Source CORD-19 dataset by fully automating the procedure of information extraction using SciBERT. The best latent entity representations are then found by benchnmarking different KG embedding techniques on the task of link prediction using a Graph Convolution Network Auto Encoder (GCN-AE). We demonstrate the utility of ERLKG with respect to COVID-19 through multiple qualitative evaluations. Due to the lack of a gold standard, we propose a relatively large intrinsic evaluation dataset for COVID-19 and use it for validating the top two performing KG embedding techniques. We find TransD to be the best performing KG embedding technique with Pearson and Spearman correlation scores of 0.4348 and 0.4570 respectively. We demonstrate that a considerable number of ERLKG’s top protein, chemical and disease predictions are currently in consideration for COVID-19 related research.</abstract>
<identifier type="citekey">basu-etal-2020-erlkg</identifier>
<identifier type="doi">10.18653/v1/2020.sdp-1.15</identifier>
<location>
<url>https://aclanthology.org/2020.sdp-1.15</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>127</start>
<end>137</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ERLKG: Entity Representation Learning and Knowledge Graph based association analysis of COVID-19 through mining of unstructured biomedical corpora
%A Basu, Sayantan
%A Chakraborty, Sinchani
%A Hassan, Atif
%A Siddique, Sana
%A Anand, Ashish
%S Proceedings of the First Workshop on Scholarly Document Processing
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F basu-etal-2020-erlkg
%X We introduce a generic, human-out-of-the-loop pipeline, ERLKG, to perform rapid association analysis of any biomedical entity with other existing entities from a corpora of the same domain. Our pipeline consists of a Knowledge Graph (KG) created from the Open Source CORD-19 dataset by fully automating the procedure of information extraction using SciBERT. The best latent entity representations are then found by benchnmarking different KG embedding techniques on the task of link prediction using a Graph Convolution Network Auto Encoder (GCN-AE). We demonstrate the utility of ERLKG with respect to COVID-19 through multiple qualitative evaluations. Due to the lack of a gold standard, we propose a relatively large intrinsic evaluation dataset for COVID-19 and use it for validating the top two performing KG embedding techniques. We find TransD to be the best performing KG embedding technique with Pearson and Spearman correlation scores of 0.4348 and 0.4570 respectively. We demonstrate that a considerable number of ERLKG’s top protein, chemical and disease predictions are currently in consideration for COVID-19 related research.
%R 10.18653/v1/2020.sdp-1.15
%U https://aclanthology.org/2020.sdp-1.15
%U https://doi.org/10.18653/v1/2020.sdp-1.15
%P 127-137
Markdown (Informal)
[ERLKG: Entity Representation Learning and Knowledge Graph based association analysis of COVID-19 through mining of unstructured biomedical corpora](https://aclanthology.org/2020.sdp-1.15) (Basu et al., sdp 2020)
ACL