@inproceedings{saeedi-etal-2022-cs,
title = "{CS}/{NLP} at {S}em{E}val-2022 Task 4: Effective Data Augmentation Methods for Patronizing Language Detection and Multi-label Classification with {R}o{BERT}a and {GPT}3",
author = "Saeedi, Daniel and
Saeedi, Sirwe and
Panahi, Aliakbar and
C.M. Fong, Alvis",
editor = "Emerson, Guy and
Schluter, Natalie and
Stanovsky, Gabriel and
Kumar, Ritesh and
Palmer, Alexis and
Schneider, Nathan and
Singh, Siddharth and
Ratan, Shyam",
booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.semeval-1.69/",
doi = "10.18653/v1/2022.semeval-1.69",
pages = "503--508",
abstract = "This paper presents a combination of data augmentation methods to boost the performance of state-of-the-art transformer-based language models for Patronizing and Condescending Language (PCL) detection and multi-label PCL classification tasks. These tasks are inherently different from sentiment analysis because positive/negative hidden attitudes in the context will not necessarily be considered positive/negative for PCL tasks. The oblation study observes that the imbalance degree of PCL dataset is in the extreme range. This paper presents a modified version of the sentence paraphrasing deep learning model (PEGASUS) to tackle the limitation of maximum sequence length. The proposed algorithm has no specific maximum input length to paraphrase sequences. Our augmented underrepresented class of annotated data achieved competitive results among top-16 SemEval-2022 participants. This paper`s approaches rely on fine-tuning pretrained RoBERTa and GPT3 models such as Davinci and Curie engines with an extra-enriched PCL dataset. Furthermore, we discuss Few-Shot learning technique to overcome the limitation of low-resource NLP problems."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saeedi-etal-2022-cs">
<titleInfo>
<title>CS/NLP at SemEval-2022 Task 4: Effective Data Augmentation Methods for Patronizing Language Detection and Multi-label Classification with RoBERTa and GPT3</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Saeedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirwe</namePart>
<namePart type="family">Saeedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aliakbar</namePart>
<namePart type="family">Panahi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alvis</namePart>
<namePart type="family">C.M. Fong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a combination of data augmentation methods to boost the performance of state-of-the-art transformer-based language models for Patronizing and Condescending Language (PCL) detection and multi-label PCL classification tasks. These tasks are inherently different from sentiment analysis because positive/negative hidden attitudes in the context will not necessarily be considered positive/negative for PCL tasks. The oblation study observes that the imbalance degree of PCL dataset is in the extreme range. This paper presents a modified version of the sentence paraphrasing deep learning model (PEGASUS) to tackle the limitation of maximum sequence length. The proposed algorithm has no specific maximum input length to paraphrase sequences. Our augmented underrepresented class of annotated data achieved competitive results among top-16 SemEval-2022 participants. This paper‘s approaches rely on fine-tuning pretrained RoBERTa and GPT3 models such as Davinci and Curie engines with an extra-enriched PCL dataset. Furthermore, we discuss Few-Shot learning technique to overcome the limitation of low-resource NLP problems.</abstract>
<identifier type="citekey">saeedi-etal-2022-cs</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.69</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.69/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>503</start>
<end>508</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CS/NLP at SemEval-2022 Task 4: Effective Data Augmentation Methods for Patronizing Language Detection and Multi-label Classification with RoBERTa and GPT3
%A Saeedi, Daniel
%A Saeedi, Sirwe
%A Panahi, Aliakbar
%A C.M. Fong, Alvis
%Y Emerson, Guy
%Y Schluter, Natalie
%Y Stanovsky, Gabriel
%Y Kumar, Ritesh
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F saeedi-etal-2022-cs
%X This paper presents a combination of data augmentation methods to boost the performance of state-of-the-art transformer-based language models for Patronizing and Condescending Language (PCL) detection and multi-label PCL classification tasks. These tasks are inherently different from sentiment analysis because positive/negative hidden attitudes in the context will not necessarily be considered positive/negative for PCL tasks. The oblation study observes that the imbalance degree of PCL dataset is in the extreme range. This paper presents a modified version of the sentence paraphrasing deep learning model (PEGASUS) to tackle the limitation of maximum sequence length. The proposed algorithm has no specific maximum input length to paraphrase sequences. Our augmented underrepresented class of annotated data achieved competitive results among top-16 SemEval-2022 participants. This paper‘s approaches rely on fine-tuning pretrained RoBERTa and GPT3 models such as Davinci and Curie engines with an extra-enriched PCL dataset. Furthermore, we discuss Few-Shot learning technique to overcome the limitation of low-resource NLP problems.
%R 10.18653/v1/2022.semeval-1.69
%U https://aclanthology.org/2022.semeval-1.69/
%U https://doi.org/10.18653/v1/2022.semeval-1.69
%P 503-508
Markdown (Informal)
[CS/NLP at SemEval-2022 Task 4: Effective Data Augmentation Methods for Patronizing Language Detection and Multi-label Classification with RoBERTa and GPT3](https://aclanthology.org/2022.semeval-1.69/) (Saeedi et al., SemEval 2022)
ACL