@inproceedings{doan-bao-etal-2020-sunbear,
title = "{S}un{B}ear at {WNUT}-2020 Task 2: Improving {BERT}-Based Noisy Text Classification with Knowledge of the Data domain",
author = "Doan Bao, Linh and
Nguyen, Viet Anh and
Pham Huu, Quang",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wnut-1.73",
doi = "10.18653/v1/2020.wnut-1.73",
pages = "485--490",
abstract = "This paper proposes an improved custom model for WNUT task 2: Identification of Informative COVID-19 English Tweet. We improve experiment with the effectiveness of fine-tuning methodologies for state-of-the-art language model RoBERTa. We make a preliminary instantiation of this formal model for the text classification approaches. With appropriate training techniques, our model is able to achieve 0.9218 F1-score on public validation set and the ensemble version settles at top 9 F1-score (0.9005) and top 2 Recall (0.9301) on private test set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="doan-bao-etal-2020-sunbear">
<titleInfo>
<title>SunBear at WNUT-2020 Task 2: Improving BERT-Based Noisy Text Classification with Knowledge of the Data domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Linh</namePart>
<namePart type="family">Doan Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viet</namePart>
<namePart type="given">Anh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quang</namePart>
<namePart type="family">Pham Huu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</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>This paper proposes an improved custom model for WNUT task 2: Identification of Informative COVID-19 English Tweet. We improve experiment with the effectiveness of fine-tuning methodologies for state-of-the-art language model RoBERTa. We make a preliminary instantiation of this formal model for the text classification approaches. With appropriate training techniques, our model is able to achieve 0.9218 F1-score on public validation set and the ensemble version settles at top 9 F1-score (0.9005) and top 2 Recall (0.9301) on private test set.</abstract>
<identifier type="citekey">doan-bao-etal-2020-sunbear</identifier>
<identifier type="doi">10.18653/v1/2020.wnut-1.73</identifier>
<location>
<url>https://aclanthology.org/2020.wnut-1.73</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>485</start>
<end>490</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SunBear at WNUT-2020 Task 2: Improving BERT-Based Noisy Text Classification with Knowledge of the Data domain
%A Doan Bao, Linh
%A Nguyen, Viet Anh
%A Pham Huu, Quang
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F doan-bao-etal-2020-sunbear
%X This paper proposes an improved custom model for WNUT task 2: Identification of Informative COVID-19 English Tweet. We improve experiment with the effectiveness of fine-tuning methodologies for state-of-the-art language model RoBERTa. We make a preliminary instantiation of this formal model for the text classification approaches. With appropriate training techniques, our model is able to achieve 0.9218 F1-score on public validation set and the ensemble version settles at top 9 F1-score (0.9005) and top 2 Recall (0.9301) on private test set.
%R 10.18653/v1/2020.wnut-1.73
%U https://aclanthology.org/2020.wnut-1.73
%U https://doi.org/10.18653/v1/2020.wnut-1.73
%P 485-490
Markdown (Informal)
[SunBear at WNUT-2020 Task 2: Improving BERT-Based Noisy Text Classification with Knowledge of the Data domain](https://aclanthology.org/2020.wnut-1.73) (Doan Bao et al., WNUT 2020)
ACL