@inproceedings{ishihara-shirai-2022-nikkei,
title = "{N}ikkei at {S}em{E}val-2022 Task 8: Exploring {BERT}-based Bi-Encoder Approach for Pairwise Multilingual News Article Similarity",
author = "Ishihara, Shotaro and
Shirai, Hono",
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-1.171",
doi = "10.18653/v1/2022.semeval-1.171",
pages = "1208--1214",
abstract = "This paper describes our system in SemEval-2022 Task 8, where participants were required to predict the similarity of two multilingual news articles. In the task of pairwise sentence and document scoring, there are two main approaches: Cross-Encoder, which inputs pairs of texts into a single encoder, and Bi-Encoder, which encodes each input independently. The former method often achieves higher performance, but the latter gave us a better result in SemEval-2022 Task 8. This paper presents our exploration of BERT-based Bi-Encoder approach for this task, and there are several findings such as pretrained models, pooling methods, translation, data separation, and the number of tokens. The weighted average ensemble of the four models achieved the competitive result and ranked in the top 12.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ishihara-shirai-2022-nikkei">
<titleInfo>
<title>Nikkei at SemEval-2022 Task 8: Exploring BERT-based Bi-Encoder Approach for Pairwise Multilingual News Article Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shotaro</namePart>
<namePart type="family">Ishihara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hono</namePart>
<namePart type="family">Shirai</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 describes our system in SemEval-2022 Task 8, where participants were required to predict the similarity of two multilingual news articles. In the task of pairwise sentence and document scoring, there are two main approaches: Cross-Encoder, which inputs pairs of texts into a single encoder, and Bi-Encoder, which encodes each input independently. The former method often achieves higher performance, but the latter gave us a better result in SemEval-2022 Task 8. This paper presents our exploration of BERT-based Bi-Encoder approach for this task, and there are several findings such as pretrained models, pooling methods, translation, data separation, and the number of tokens. The weighted average ensemble of the four models achieved the competitive result and ranked in the top 12.</abstract>
<identifier type="citekey">ishihara-shirai-2022-nikkei</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.171</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.171</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1208</start>
<end>1214</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Nikkei at SemEval-2022 Task 8: Exploring BERT-based Bi-Encoder Approach for Pairwise Multilingual News Article Similarity
%A Ishihara, Shotaro
%A Shirai, Hono
%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 ishihara-shirai-2022-nikkei
%X This paper describes our system in SemEval-2022 Task 8, where participants were required to predict the similarity of two multilingual news articles. In the task of pairwise sentence and document scoring, there are two main approaches: Cross-Encoder, which inputs pairs of texts into a single encoder, and Bi-Encoder, which encodes each input independently. The former method often achieves higher performance, but the latter gave us a better result in SemEval-2022 Task 8. This paper presents our exploration of BERT-based Bi-Encoder approach for this task, and there are several findings such as pretrained models, pooling methods, translation, data separation, and the number of tokens. The weighted average ensemble of the four models achieved the competitive result and ranked in the top 12.
%R 10.18653/v1/2022.semeval-1.171
%U https://aclanthology.org/2022.semeval-1.171
%U https://doi.org/10.18653/v1/2022.semeval-1.171
%P 1208-1214
Markdown (Informal)
[Nikkei at SemEval-2022 Task 8: Exploring BERT-based Bi-Encoder Approach for Pairwise Multilingual News Article Similarity](https://aclanthology.org/2022.semeval-1.171) (Ishihara & Shirai, SemEval 2022)
ACL