@inproceedings{thillaisundaram-togia-2019-biomedical,
title = "Biomedical relation extraction with pre-trained language representations and minimal task-specific architecture",
author = "Thillaisundaram, Ashok and
Togia, Theodosia",
editor = "Jin-Dong, Kim and
Claire, N{\'e}dellec and
Robert, Bossy and
Louise, Del{\'e}ger",
booktitle = "Proceedings of the 5th Workshop on BioNLP Open Shared Tasks",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5713",
doi = "10.18653/v1/D19-5713",
pages = "84--89",
abstract = "This paper presents our participation in the AGAC Track from the 2019 BioNLP Open Shared Tasks. We provide a solution for Task 3, which aims to extract {``}gene - function change - disease{''} triples, where {``}gene{''} and {``}disease{''} are mentions of particular genes and diseases respectively and {``}function change{''} is one of four pre-defined relationship types. Our system extends BERT (Devlin et al., 2018), a state-of-the-art language model, which learns contextual language representations from a large unlabelled corpus and whose parameters can be fine-tuned to solve specific tasks with minimal additional architecture. We encode the pair of mentions and their textual context as two consecutive sequences in BERT, separated by a special symbol. We then use a single linear layer to classify their relationship into five classes (four pre-defined, as well as {`}no relation{'}). Despite considerable class imbalance, our system significantly outperforms a random baseline while relying on an extremely simple setup with no specially engineered features.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thillaisundaram-togia-2019-biomedical">
<titleInfo>
<title>Biomedical relation extraction with pre-trained language representations and minimal task-specific architecture</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ashok</namePart>
<namePart type="family">Thillaisundaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Theodosia</namePart>
<namePart type="family">Togia</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 5th Workshop on BioNLP Open Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kim</namePart>
<namePart type="family">Jin-Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nédellec</namePart>
<namePart type="family">Claire</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bossy</namePart>
<namePart type="family">Robert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deléger</namePart>
<namePart type="family">Louise</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our participation in the AGAC Track from the 2019 BioNLP Open Shared Tasks. We provide a solution for Task 3, which aims to extract “gene - function change - disease” triples, where “gene” and “disease” are mentions of particular genes and diseases respectively and “function change” is one of four pre-defined relationship types. Our system extends BERT (Devlin et al., 2018), a state-of-the-art language model, which learns contextual language representations from a large unlabelled corpus and whose parameters can be fine-tuned to solve specific tasks with minimal additional architecture. We encode the pair of mentions and their textual context as two consecutive sequences in BERT, separated by a special symbol. We then use a single linear layer to classify their relationship into five classes (four pre-defined, as well as ‘no relation’). Despite considerable class imbalance, our system significantly outperforms a random baseline while relying on an extremely simple setup with no specially engineered features.</abstract>
<identifier type="citekey">thillaisundaram-togia-2019-biomedical</identifier>
<identifier type="doi">10.18653/v1/D19-5713</identifier>
<location>
<url>https://aclanthology.org/D19-5713</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>84</start>
<end>89</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Biomedical relation extraction with pre-trained language representations and minimal task-specific architecture
%A Thillaisundaram, Ashok
%A Togia, Theodosia
%Y Jin-Dong, Kim
%Y Claire, Nédellec
%Y Robert, Bossy
%Y Louise, Deléger
%S Proceedings of the 5th Workshop on BioNLP Open Shared Tasks
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F thillaisundaram-togia-2019-biomedical
%X This paper presents our participation in the AGAC Track from the 2019 BioNLP Open Shared Tasks. We provide a solution for Task 3, which aims to extract “gene - function change - disease” triples, where “gene” and “disease” are mentions of particular genes and diseases respectively and “function change” is one of four pre-defined relationship types. Our system extends BERT (Devlin et al., 2018), a state-of-the-art language model, which learns contextual language representations from a large unlabelled corpus and whose parameters can be fine-tuned to solve specific tasks with minimal additional architecture. We encode the pair of mentions and their textual context as two consecutive sequences in BERT, separated by a special symbol. We then use a single linear layer to classify their relationship into five classes (four pre-defined, as well as ‘no relation’). Despite considerable class imbalance, our system significantly outperforms a random baseline while relying on an extremely simple setup with no specially engineered features.
%R 10.18653/v1/D19-5713
%U https://aclanthology.org/D19-5713
%U https://doi.org/10.18653/v1/D19-5713
%P 84-89
Markdown (Informal)
[Biomedical relation extraction with pre-trained language representations and minimal task-specific architecture](https://aclanthology.org/D19-5713) (Thillaisundaram & Togia, BioNLP 2019)
ACL