@inproceedings{ellendorff-etal-2019-approaching,
title = "Approaching {SMM}4{H} with Merged Models and Multi-task Learning",
author = {Ellendorff, Tilia and
Furrer, Lenz and
Colic, Nicola and
Aepli, No{\"e}mi and
Rinaldi, Fabio},
editor = "Weissenbacher, Davy and
Gonzalez-Hernandez, Graciela",
booktitle = "Proceedings of the Fourth Social Media Mining for Health Applications ({\#}SMM4H) Workshop {\&} Shared Task",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-3208",
doi = "10.18653/v1/W19-3208",
pages = "58--61",
abstract = "We describe our submissions to the 4th edition of the Social Media Mining for Health Applications (SMM4H) shared task. Our team (UZH) participated in two sub-tasks: Automatic classifications of adverse effects mentions in tweets (Task 1) and Generalizable identification of personal health experience mentions (Task 4). For our submissions, we exploited ensembles based on a pre-trained language representation with a neural transformer architecture (BERT) (Tasks 1 and 4) and a CNN-BiLSTM(-CRF) network within a multi-task learning scenario (Task 1). These systems are placed on top of a carefully crafted pipeline of domain-specific preprocessing steps.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ellendorff-etal-2019-approaching">
<titleInfo>
<title>Approaching SMM4H with Merged Models and Multi-task Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tilia</namePart>
<namePart type="family">Ellendorff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lenz</namePart>
<namePart type="family">Furrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicola</namePart>
<namePart type="family">Colic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noëmi</namePart>
<namePart type="family">Aepli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Davy</namePart>
<namePart type="family">Weissenbacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe our submissions to the 4th edition of the Social Media Mining for Health Applications (SMM4H) shared task. Our team (UZH) participated in two sub-tasks: Automatic classifications of adverse effects mentions in tweets (Task 1) and Generalizable identification of personal health experience mentions (Task 4). For our submissions, we exploited ensembles based on a pre-trained language representation with a neural transformer architecture (BERT) (Tasks 1 and 4) and a CNN-BiLSTM(-CRF) network within a multi-task learning scenario (Task 1). These systems are placed on top of a carefully crafted pipeline of domain-specific preprocessing steps.</abstract>
<identifier type="citekey">ellendorff-etal-2019-approaching</identifier>
<identifier type="doi">10.18653/v1/W19-3208</identifier>
<location>
<url>https://aclanthology.org/W19-3208</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>58</start>
<end>61</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Approaching SMM4H with Merged Models and Multi-task Learning
%A Ellendorff, Tilia
%A Furrer, Lenz
%A Colic, Nicola
%A Aepli, Noëmi
%A Rinaldi, Fabio
%Y Weissenbacher, Davy
%Y Gonzalez-Hernandez, Graciela
%S Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F ellendorff-etal-2019-approaching
%X We describe our submissions to the 4th edition of the Social Media Mining for Health Applications (SMM4H) shared task. Our team (UZH) participated in two sub-tasks: Automatic classifications of adverse effects mentions in tweets (Task 1) and Generalizable identification of personal health experience mentions (Task 4). For our submissions, we exploited ensembles based on a pre-trained language representation with a neural transformer architecture (BERT) (Tasks 1 and 4) and a CNN-BiLSTM(-CRF) network within a multi-task learning scenario (Task 1). These systems are placed on top of a carefully crafted pipeline of domain-specific preprocessing steps.
%R 10.18653/v1/W19-3208
%U https://aclanthology.org/W19-3208
%U https://doi.org/10.18653/v1/W19-3208
%P 58-61
Markdown (Informal)
[Approaching SMM4H with Merged Models and Multi-task Learning](https://aclanthology.org/W19-3208) (Ellendorff et al., ACL 2019)
ACL
- Tilia Ellendorff, Lenz Furrer, Nicola Colic, Noëmi Aepli, and Fabio Rinaldi. 2019. Approaching SMM4H with Merged Models and Multi-task Learning. In Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task, pages 58–61, Florence, Italy. Association for Computational Linguistics.