@inproceedings{luo-etal-2022-tcu,
title = "{TCU} at {S}em{E}val-2022 Task 8: A Stacking Ensemble Transformer Model for Multilingual News Article Similarity",
author = "Luo, Xiang and
Niu, Yanqing and
Zhu, Boer",
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-1.170/",
doi = "10.18653/v1/2022.semeval-1.170",
pages = "1202--1207",
abstract = "Previous studies focus on measuring the degree of similarity of textsby using traditional machine learning methods, such as Support Vector Regression (SVR). Based on Transformers, this paper describes our contribution to SemEval-2022 Task 8 Multilingual News Article Similarity. The similarity of multilingual news articles requires a regression prediction on the similarity of multilingual articles, rather than a classification for judging text similarity. This paper mainly describes the architecture of the model and how to adjust the parameters in the experiment and strengthen the generalization ability. In this paper, we implement and construct different models through transformer-based models. We applied different transformer-based models, as well as ensemble them together by using ensemble learning. To avoid the overfit, we focus on the adjustment of parameters and the increase of generalization ability in our experiments. In the last submitted contest, we achieve a score of 0.715 and rank the 21st place."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luo-etal-2022-tcu">
<titleInfo>
<title>TCU at SemEval-2022 Task 8: A Stacking Ensemble Transformer Model for Multilingual News Article Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanqing</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boer</namePart>
<namePart type="family">Zhu</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>Previous studies focus on measuring the degree of similarity of textsby using traditional machine learning methods, such as Support Vector Regression (SVR). Based on Transformers, this paper describes our contribution to SemEval-2022 Task 8 Multilingual News Article Similarity. The similarity of multilingual news articles requires a regression prediction on the similarity of multilingual articles, rather than a classification for judging text similarity. This paper mainly describes the architecture of the model and how to adjust the parameters in the experiment and strengthen the generalization ability. In this paper, we implement and construct different models through transformer-based models. We applied different transformer-based models, as well as ensemble them together by using ensemble learning. To avoid the overfit, we focus on the adjustment of parameters and the increase of generalization ability in our experiments. In the last submitted contest, we achieve a score of 0.715 and rank the 21st place.</abstract>
<identifier type="citekey">luo-etal-2022-tcu</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.170</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.170/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1202</start>
<end>1207</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TCU at SemEval-2022 Task 8: A Stacking Ensemble Transformer Model for Multilingual News Article Similarity
%A Luo, Xiang
%A Niu, Yanqing
%A Zhu, Boer
%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 luo-etal-2022-tcu
%X Previous studies focus on measuring the degree of similarity of textsby using traditional machine learning methods, such as Support Vector Regression (SVR). Based on Transformers, this paper describes our contribution to SemEval-2022 Task 8 Multilingual News Article Similarity. The similarity of multilingual news articles requires a regression prediction on the similarity of multilingual articles, rather than a classification for judging text similarity. This paper mainly describes the architecture of the model and how to adjust the parameters in the experiment and strengthen the generalization ability. In this paper, we implement and construct different models through transformer-based models. We applied different transformer-based models, as well as ensemble them together by using ensemble learning. To avoid the overfit, we focus on the adjustment of parameters and the increase of generalization ability in our experiments. In the last submitted contest, we achieve a score of 0.715 and rank the 21st place.
%R 10.18653/v1/2022.semeval-1.170
%U https://aclanthology.org/2022.semeval-1.170/
%U https://doi.org/10.18653/v1/2022.semeval-1.170
%P 1202-1207
Markdown (Informal)
[TCU at SemEval-2022 Task 8: A Stacking Ensemble Transformer Model for Multilingual News Article Similarity](https://aclanthology.org/2022.semeval-1.170/) (Luo et al., SemEval 2022)
ACL