@inproceedings{chen-etal-2022-itnlp2022,
title = "{ITNLP}2022 at {S}em{E}val-2022 Task 8: Pre-trained Model with Data Augmentation and Voting for Multilingual News Similarity",
author = "Chen, Zhongan and
Chen, Weiwei and
Sun, YunLong and
Xu, Hongqing and
Zhou, Shuzhe and
Chen, Bohan and
Sun, Chengjie and
Liu, Yuanchao",
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-1.167",
doi = "10.18653/v1/2022.semeval-1.167",
pages = "1184--1189",
abstract = "This article introduces a system to solve the SemEval 2022 Task 8: Multilingual News Article Similarity. The task focuses on the consistency of events reported in two news articles. The system consists of a pre-trained model(e.g., INFOXLM and XLM-RoBERTa) to extract multilingual news features, following fully-connected networks to measure the similarity. In addition, data augmentation and Ten Fold Voting are used to enhance the model. Our final submitted model is an ensemble of three base models, with a Pearson value of 0.784 on the test dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-itnlp2022">
<titleInfo>
<title>ITNLP2022 at SemEval-2022 Task 8: Pre-trained Model with Data Augmentation and Voting for Multilingual News Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhongan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiwei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">YunLong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongqing</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuzhe</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bohan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengjie</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanchao</namePart>
<namePart type="family">Liu</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 article introduces a system to solve the SemEval 2022 Task 8: Multilingual News Article Similarity. The task focuses on the consistency of events reported in two news articles. The system consists of a pre-trained model(e.g., INFOXLM and XLM-RoBERTa) to extract multilingual news features, following fully-connected networks to measure the similarity. In addition, data augmentation and Ten Fold Voting are used to enhance the model. Our final submitted model is an ensemble of three base models, with a Pearson value of 0.784 on the test dataset.</abstract>
<identifier type="citekey">chen-etal-2022-itnlp2022</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.167</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.167</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1184</start>
<end>1189</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ITNLP2022 at SemEval-2022 Task 8: Pre-trained Model with Data Augmentation and Voting for Multilingual News Similarity
%A Chen, Zhongan
%A Chen, Weiwei
%A Sun, YunLong
%A Xu, Hongqing
%A Zhou, Shuzhe
%A Chen, Bohan
%A Sun, Chengjie
%A Liu, Yuanchao
%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 chen-etal-2022-itnlp2022
%X This article introduces a system to solve the SemEval 2022 Task 8: Multilingual News Article Similarity. The task focuses on the consistency of events reported in two news articles. The system consists of a pre-trained model(e.g., INFOXLM and XLM-RoBERTa) to extract multilingual news features, following fully-connected networks to measure the similarity. In addition, data augmentation and Ten Fold Voting are used to enhance the model. Our final submitted model is an ensemble of three base models, with a Pearson value of 0.784 on the test dataset.
%R 10.18653/v1/2022.semeval-1.167
%U https://aclanthology.org/2022.semeval-1.167
%U https://doi.org/10.18653/v1/2022.semeval-1.167
%P 1184-1189
Markdown (Informal)
[ITNLP2022 at SemEval-2022 Task 8: Pre-trained Model with Data Augmentation and Voting for Multilingual News Similarity](https://aclanthology.org/2022.semeval-1.167) (Chen et al., SemEval 2022)
ACL
- Zhongan Chen, Weiwei Chen, YunLong Sun, Hongqing Xu, Shuzhe Zhou, Bohan Chen, Chengjie Sun, and Yuanchao Liu. 2022. ITNLP2022 at SemEval-2022 Task 8: Pre-trained Model with Data Augmentation and Voting for Multilingual News Similarity. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1184–1189, Seattle, United States. Association for Computational Linguistics.