@inproceedings{portelli-etal-2022-generalizing,
title = "Generalizing over Long Tail Concepts for Medical Term Normalization",
author = "Portelli, Beatrice and
Scaboro, Simone and
Santus, Enrico and
Sedghamiz, Hooman and
Chersoni, Emmanuele and
Serra, Giuseppe",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.588",
doi = "10.18653/v1/2022.emnlp-main.588",
pages = "8580--8591",
abstract = "Medical term normalization consists in mapping a piece of text to a large number of output classes.Given the small size of the annotated datasets and the extremely long tail distribution of the concepts, it is of utmost importance to develop models that are capable to generalize to scarce or unseen concepts.An important attribute of most target ontologies is their hierarchical structure. In this paper we introduce a simple and effective learning strategy that leverages such information to enhance the generalizability of both discriminative and generative models.The evaluation shows that the proposed strategy produces state-of-the-art performance on seen concepts and consistent improvements on unseen ones, allowing also for efficient zero-shot knowledge transfer across text typologies and datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="portelli-etal-2022-generalizing">
<titleInfo>
<title>Generalizing over Long Tail Concepts for Medical Term Normalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Beatrice</namePart>
<namePart type="family">Portelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Scaboro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hooman</namePart>
<namePart type="family">Sedghamiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuele</namePart>
<namePart type="family">Chersoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Serra</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 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</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</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Medical term normalization consists in mapping a piece of text to a large number of output classes.Given the small size of the annotated datasets and the extremely long tail distribution of the concepts, it is of utmost importance to develop models that are capable to generalize to scarce or unseen concepts.An important attribute of most target ontologies is their hierarchical structure. In this paper we introduce a simple and effective learning strategy that leverages such information to enhance the generalizability of both discriminative and generative models.The evaluation shows that the proposed strategy produces state-of-the-art performance on seen concepts and consistent improvements on unseen ones, allowing also for efficient zero-shot knowledge transfer across text typologies and datasets.</abstract>
<identifier type="citekey">portelli-etal-2022-generalizing</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.588</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.588</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>8580</start>
<end>8591</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generalizing over Long Tail Concepts for Medical Term Normalization
%A Portelli, Beatrice
%A Scaboro, Simone
%A Santus, Enrico
%A Sedghamiz, Hooman
%A Chersoni, Emmanuele
%A Serra, Giuseppe
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F portelli-etal-2022-generalizing
%X Medical term normalization consists in mapping a piece of text to a large number of output classes.Given the small size of the annotated datasets and the extremely long tail distribution of the concepts, it is of utmost importance to develop models that are capable to generalize to scarce or unseen concepts.An important attribute of most target ontologies is their hierarchical structure. In this paper we introduce a simple and effective learning strategy that leverages such information to enhance the generalizability of both discriminative and generative models.The evaluation shows that the proposed strategy produces state-of-the-art performance on seen concepts and consistent improvements on unseen ones, allowing also for efficient zero-shot knowledge transfer across text typologies and datasets.
%R 10.18653/v1/2022.emnlp-main.588
%U https://aclanthology.org/2022.emnlp-main.588
%U https://doi.org/10.18653/v1/2022.emnlp-main.588
%P 8580-8591
Markdown (Informal)
[Generalizing over Long Tail Concepts for Medical Term Normalization](https://aclanthology.org/2022.emnlp-main.588) (Portelli et al., EMNLP 2022)
ACL
- Beatrice Portelli, Simone Scaboro, Enrico Santus, Hooman Sedghamiz, Emmanuele Chersoni, and Giuseppe Serra. 2022. Generalizing over Long Tail Concepts for Medical Term Normalization. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8580–8591, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.