@inproceedings{bai-zhou-2020-automatic,
title = "Automatic Detecting for Health-related {T}witter Data with {B}io{BERT}",
author = "Bai, Yang and
Zhou, Xiaobing",
editor = "Gonzalez-Hernandez, Graciela and
Klein, Ari Z. and
Flores, Ivan and
Weissenbacher, Davy and
Magge, Arjun and
O'Connor, Karen and
Sarker, Abeed and
Minard, Anne-Lyse and
Tutubalina, Elena and
Miftahutdinov, Zulfat and
Alimova, Ilseyar",
booktitle = "Proceedings of the Fifth Social Media Mining for Health Applications Workshop {\&} Shared Task",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.smm4h-1.10",
pages = "63--69",
abstract = "Social media used for health applications usually contains a large amount of data posted by users, which brings various challenges to NLP, such as spoken language, spelling errors, novel/creative phrases, etc. In this paper, we describe our system submitted to SMM4H 2020: Social Media Mining for Health Applications Shared Task which consists of five sub-tasks. We participate in subtask 1, subtask 2-English, and subtask 5. Our final submitted approach is an ensemble of various fine-tuned transformer-based models. We illustrate that these approaches perform well in imbalanced datasets (For example, the class ratio is 1:10 in subtask 2), but our model performance is not good in extremely imbalanced datasets (For example, the class ratio is 1:400 in subtask 1). Finally, in subtask 1, our result is lower than the average score, in subtask 2-English, our result is higher than the average score, and in subtask 5, our result achieves the highest score. The code is available online.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bai-zhou-2020-automatic">
<titleInfo>
<title>Automatic Detecting for Health-related Twitter Data with BioBERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ari</namePart>
<namePart type="given">Z</namePart>
<namePart type="family">Klein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Arjun</namePart>
<namePart type="family">Magge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">O’Connor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abeed</namePart>
<namePart type="family">Sarker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Lyse</namePart>
<namePart type="family">Minard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Tutubalina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zulfat</namePart>
<namePart type="family">Miftahutdinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilseyar</namePart>
<namePart type="family">Alimova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Social media used for health applications usually contains a large amount of data posted by users, which brings various challenges to NLP, such as spoken language, spelling errors, novel/creative phrases, etc. In this paper, we describe our system submitted to SMM4H 2020: Social Media Mining for Health Applications Shared Task which consists of five sub-tasks. We participate in subtask 1, subtask 2-English, and subtask 5. Our final submitted approach is an ensemble of various fine-tuned transformer-based models. We illustrate that these approaches perform well in imbalanced datasets (For example, the class ratio is 1:10 in subtask 2), but our model performance is not good in extremely imbalanced datasets (For example, the class ratio is 1:400 in subtask 1). Finally, in subtask 1, our result is lower than the average score, in subtask 2-English, our result is higher than the average score, and in subtask 5, our result achieves the highest score. The code is available online.</abstract>
<identifier type="citekey">bai-zhou-2020-automatic</identifier>
<location>
<url>https://aclanthology.org/2020.smm4h-1.10</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>63</start>
<end>69</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Detecting for Health-related Twitter Data with BioBERT
%A Bai, Yang
%A Zhou, Xiaobing
%Y Gonzalez-Hernandez, Graciela
%Y Klein, Ari Z.
%Y Flores, Ivan
%Y Weissenbacher, Davy
%Y Magge, Arjun
%Y O’Connor, Karen
%Y Sarker, Abeed
%Y Minard, Anne-Lyse
%Y Tutubalina, Elena
%Y Miftahutdinov, Zulfat
%Y Alimova, Ilseyar
%S Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F bai-zhou-2020-automatic
%X Social media used for health applications usually contains a large amount of data posted by users, which brings various challenges to NLP, such as spoken language, spelling errors, novel/creative phrases, etc. In this paper, we describe our system submitted to SMM4H 2020: Social Media Mining for Health Applications Shared Task which consists of five sub-tasks. We participate in subtask 1, subtask 2-English, and subtask 5. Our final submitted approach is an ensemble of various fine-tuned transformer-based models. We illustrate that these approaches perform well in imbalanced datasets (For example, the class ratio is 1:10 in subtask 2), but our model performance is not good in extremely imbalanced datasets (For example, the class ratio is 1:400 in subtask 1). Finally, in subtask 1, our result is lower than the average score, in subtask 2-English, our result is higher than the average score, and in subtask 5, our result achieves the highest score. The code is available online.
%U https://aclanthology.org/2020.smm4h-1.10
%P 63-69
Markdown (Informal)
[Automatic Detecting for Health-related Twitter Data with BioBERT](https://aclanthology.org/2020.smm4h-1.10) (Bai & Zhou, SMM4H 2020)
ACL