@inproceedings{arjun-etal-2021-precog,
title = "Precog-{LTRC}-{IIITH} at {G}erm{E}val 2021: Ensembling Pre-Trained Language Models with Feature Engineering",
author = "Arjun, T. H. and
A., Arvindh and
Ponnurangam, Kumaraguru",
editor = "Risch, Julian and
Stoll, Anke and
Wilms, Lena and
Wiegand, Michael",
booktitle = "Proceedings of the GermEval 2021 Shared Task on the Identification of Toxic, Engaging, and Fact-Claiming Comments",
month = sep,
year = "2021",
address = "Duesseldorf, Germany",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.germeval-1.6",
pages = "39--46",
abstract = "We describe our participation in all the subtasks of the Germeval 2021 shared task on the identification of Toxic, Engaging, and Fact-Claiming Comments. Our system is an ensemble of state-of-the-art pre-trained models finetuned with carefully engineered features. We show that feature engineering and data augmentation can be helpful when the training data is sparse. We achieve an F1 score of 66.87, 68.93, and 73.91 in Toxic, Engaging, and Fact-Claiming comment identification subtasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arjun-etal-2021-precog">
<titleInfo>
<title>Precog-LTRC-IIITH at GermEval 2021: Ensembling Pre-Trained Language Models with Feature Engineering</title>
</titleInfo>
<name type="personal">
<namePart type="given">T</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Arjun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arvindh</namePart>
<namePart type="family">A.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kumaraguru</namePart>
<namePart type="family">Ponnurangam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the GermEval 2021 Shared Task on the Identification of Toxic, Engaging, and Fact-Claiming Comments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julian</namePart>
<namePart type="family">Risch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anke</namePart>
<namePart type="family">Stoll</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lena</namePart>
<namePart type="family">Wilms</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Wiegand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Duesseldorf, Germany</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe our participation in all the subtasks of the Germeval 2021 shared task on the identification of Toxic, Engaging, and Fact-Claiming Comments. Our system is an ensemble of state-of-the-art pre-trained models finetuned with carefully engineered features. We show that feature engineering and data augmentation can be helpful when the training data is sparse. We achieve an F1 score of 66.87, 68.93, and 73.91 in Toxic, Engaging, and Fact-Claiming comment identification subtasks.</abstract>
<identifier type="citekey">arjun-etal-2021-precog</identifier>
<location>
<url>https://aclanthology.org/2021.germeval-1.6</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>39</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Precog-LTRC-IIITH at GermEval 2021: Ensembling Pre-Trained Language Models with Feature Engineering
%A Arjun, T. H.
%A A., Arvindh
%A Ponnurangam, Kumaraguru
%Y Risch, Julian
%Y Stoll, Anke
%Y Wilms, Lena
%Y Wiegand, Michael
%S Proceedings of the GermEval 2021 Shared Task on the Identification of Toxic, Engaging, and Fact-Claiming Comments
%D 2021
%8 September
%I Association for Computational Linguistics
%C Duesseldorf, Germany
%F arjun-etal-2021-precog
%X We describe our participation in all the subtasks of the Germeval 2021 shared task on the identification of Toxic, Engaging, and Fact-Claiming Comments. Our system is an ensemble of state-of-the-art pre-trained models finetuned with carefully engineered features. We show that feature engineering and data augmentation can be helpful when the training data is sparse. We achieve an F1 score of 66.87, 68.93, and 73.91 in Toxic, Engaging, and Fact-Claiming comment identification subtasks.
%U https://aclanthology.org/2021.germeval-1.6
%P 39-46
Markdown (Informal)
[Precog-LTRC-IIITH at GermEval 2021: Ensembling Pre-Trained Language Models with Feature Engineering](https://aclanthology.org/2021.germeval-1.6) (Arjun et al., GermEval 2021)
ACL