@inproceedings{fivez-etal-2021-conceptual,
title = "Conceptual Grounding Constraints for Truly Robust Biomedical Name Representations",
author = "Fivez, Pieter and
Suster, Simon and
Daelemans, Walter",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.208",
doi = "10.18653/v1/2021.eacl-main.208",
pages = "2440--2450",
abstract = "Effective representation of biomedical names for downstream NLP tasks requires the encoding of both lexical as well as domain-specific semantic information. Ideally, the synonymy and semantic relatedness of names should be consistently reflected by their closeness in an embedding space. To achieve such robustness, prior research has considered multi-task objectives when training neural encoders. In this paper, we take a next step towards truly robust representations, which capture more domain-specific semantics while remaining universally applicable across different biomedical corpora and domains. To this end, we use conceptual grounding constraints which more effectively align encoded names to pretrained embeddings of their concept identifiers. These constraints are effective even when using a Deep Averaging Network, a simple feedforward encoding architecture that allows for scaling to large corpora while remaining sufficiently expressive. We empirically validate our approach using multiple tasks and benchmarks, which assess both literal synonymy as well as more general semantic relatedness.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fivez-etal-2021-conceptual">
<titleInfo>
<title>Conceptual Grounding Constraints for Truly Robust Biomedical Name Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pieter</namePart>
<namePart type="family">Fivez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Suster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walter</namePart>
<namePart type="family">Daelemans</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Effective representation of biomedical names for downstream NLP tasks requires the encoding of both lexical as well as domain-specific semantic information. Ideally, the synonymy and semantic relatedness of names should be consistently reflected by their closeness in an embedding space. To achieve such robustness, prior research has considered multi-task objectives when training neural encoders. In this paper, we take a next step towards truly robust representations, which capture more domain-specific semantics while remaining universally applicable across different biomedical corpora and domains. To this end, we use conceptual grounding constraints which more effectively align encoded names to pretrained embeddings of their concept identifiers. These constraints are effective even when using a Deep Averaging Network, a simple feedforward encoding architecture that allows for scaling to large corpora while remaining sufficiently expressive. We empirically validate our approach using multiple tasks and benchmarks, which assess both literal synonymy as well as more general semantic relatedness.</abstract>
<identifier type="citekey">fivez-etal-2021-conceptual</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.208</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.208</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>2440</start>
<end>2450</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Conceptual Grounding Constraints for Truly Robust Biomedical Name Representations
%A Fivez, Pieter
%A Suster, Simon
%A Daelemans, Walter
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F fivez-etal-2021-conceptual
%X Effective representation of biomedical names for downstream NLP tasks requires the encoding of both lexical as well as domain-specific semantic information. Ideally, the synonymy and semantic relatedness of names should be consistently reflected by their closeness in an embedding space. To achieve such robustness, prior research has considered multi-task objectives when training neural encoders. In this paper, we take a next step towards truly robust representations, which capture more domain-specific semantics while remaining universally applicable across different biomedical corpora and domains. To this end, we use conceptual grounding constraints which more effectively align encoded names to pretrained embeddings of their concept identifiers. These constraints are effective even when using a Deep Averaging Network, a simple feedforward encoding architecture that allows for scaling to large corpora while remaining sufficiently expressive. We empirically validate our approach using multiple tasks and benchmarks, which assess both literal synonymy as well as more general semantic relatedness.
%R 10.18653/v1/2021.eacl-main.208
%U https://aclanthology.org/2021.eacl-main.208
%U https://doi.org/10.18653/v1/2021.eacl-main.208
%P 2440-2450
Markdown (Informal)
[Conceptual Grounding Constraints for Truly Robust Biomedical Name Representations](https://aclanthology.org/2021.eacl-main.208) (Fivez et al., EACL 2021)
ACL