<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dima-etal-2021-transformer">
    <titleInfo>
        <title>Transformer-based Multi-Task Learning for Adverse Effect Mention Analysis in Tweets</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">George-Andrei</namePart>
        <namePart type="family">Dima</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dumitru-Clementin</namePart>
        <namePart type="family">Cercel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mihai</namePart>
        <namePart type="family">Dascalu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mexico City, Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper presents our contribution to the Social Media Mining for Health Applications Shared Task 2021. We addressed all the three subtasks of Task 1: Subtask A (classification of tweets containing adverse effects), Subtask B (extraction of text spans containing adverse effects) and Subtask C (adverse effects resolution). We explored various pre-trained transformer-based language models and we focused on a multi-task training architecture. For the first subtask, we also applied adversarial augmentation techniques and we formed model ensembles in order to improve the robustness of the prediction. Our system ranked first at Subtask B with 0.51 F1 score, 0.514 precision and 0.514 recall. For Subtask A we obtained 0.44 F1 score, 0.49 precision and 0.39 recall and for Subtask C we obtained 0.16 F1 score with 0.16 precision and 0.17 recall.</abstract>
    <identifier type="citekey">dima-etal-2021-transformer</identifier>
    <identifier type="doi">10.18653/v1/2021.smm4h-1.7</identifier>
    <location>
        <url>https://aclanthology.org/2021.smm4h-1.7</url>
    </location>
    <part>
        <date>2021-06</date>
        <extent unit="page">
            <start>44</start>
            <end>51</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Transformer-based Multi-Task Learning for Adverse Effect Mention Analysis in Tweets
%A Dima, George-Andrei
%A Cercel, Dumitru-Clementin
%A Dascalu, Mihai
%S Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task
%D 2021
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F dima-etal-2021-transformer
%X This paper presents our contribution to the Social Media Mining for Health Applications Shared Task 2021. We addressed all the three subtasks of Task 1: Subtask A (classification of tweets containing adverse effects), Subtask B (extraction of text spans containing adverse effects) and Subtask C (adverse effects resolution). We explored various pre-trained transformer-based language models and we focused on a multi-task training architecture. For the first subtask, we also applied adversarial augmentation techniques and we formed model ensembles in order to improve the robustness of the prediction. Our system ranked first at Subtask B with 0.51 F1 score, 0.514 precision and 0.514 recall. For Subtask A we obtained 0.44 F1 score, 0.49 precision and 0.39 recall and for Subtask C we obtained 0.16 F1 score with 0.16 precision and 0.17 recall.
%R 10.18653/v1/2021.smm4h-1.7
%U https://aclanthology.org/2021.smm4h-1.7
%U https://doi.org/10.18653/v1/2021.smm4h-1.7
%P 44-51

Markdown (Informal)

[Transformer-based Multi-Task Learning for Adverse Effect Mention Analysis in Tweets](https://aclanthology.org/2021.smm4h-1.7) (Dima et al., SMM4H 2021)

• Transformer-based Multi-Task Learning for Adverse Effect Mention Analysis in Tweets (Dima et al., SMM4H 2021)

ACL

• George-Andrei Dima, Dumitru-Clementin Cercel, and Mihai Dascalu. 2021. Transformer-based Multi-Task Learning for Adverse Effect Mention Analysis in Tweets. In Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task, pages 44–51, Mexico City, Mexico. Association for Computational Linguistics.