@inproceedings{pisarevskaya-zubiaga-2022-team,
title = "Team dina at {S}em{E}val-2022 Task 8: Pre-trained Language Models as Baselines for Semantic Similarity",
author = "Pisarevskaya, Dina and
Zubiaga, Arkaitz",
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-1.169/",
doi = "10.18653/v1/2022.semeval-1.169",
pages = "1196--1201",
abstract = "This paper describes the participation of the team {\textquotedblleft}dina{\textquotedblright} in the Multilingual News Similarity task at SemEval 2022. To build our system for the task, we experimented with several multilingual language models which were originally pre-trained for semantic similarity but were not further fine-tuned. We use these models in combination with state-of-the-art packages for machine translation and named entity recognition with the expectation of providing valuable input to the model. Our work assesses the applicability of such {\textquotedblleft}pure{\textquotedblright} models to solve the multilingual semantic similarity task in the case of news articles. Our best model achieved a score of 0.511, but shows that there is room for improvement."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pisarevskaya-zubiaga-2022-team">
<titleInfo>
<title>Team dina at SemEval-2022 Task 8: Pre-trained Language Models as Baselines for Semantic Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Pisarevskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arkaitz</namePart>
<namePart type="family">Zubiaga</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 the participation of the team “dina” in the Multilingual News Similarity task at SemEval 2022. To build our system for the task, we experimented with several multilingual language models which were originally pre-trained for semantic similarity but were not further fine-tuned. We use these models in combination with state-of-the-art packages for machine translation and named entity recognition with the expectation of providing valuable input to the model. Our work assesses the applicability of such “pure” models to solve the multilingual semantic similarity task in the case of news articles. Our best model achieved a score of 0.511, but shows that there is room for improvement.</abstract>
<identifier type="citekey">pisarevskaya-zubiaga-2022-team</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.169</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.169/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1196</start>
<end>1201</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team dina at SemEval-2022 Task 8: Pre-trained Language Models as Baselines for Semantic Similarity
%A Pisarevskaya, Dina
%A Zubiaga, Arkaitz
%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 pisarevskaya-zubiaga-2022-team
%X This paper describes the participation of the team “dina” in the Multilingual News Similarity task at SemEval 2022. To build our system for the task, we experimented with several multilingual language models which were originally pre-trained for semantic similarity but were not further fine-tuned. We use these models in combination with state-of-the-art packages for machine translation and named entity recognition with the expectation of providing valuable input to the model. Our work assesses the applicability of such “pure” models to solve the multilingual semantic similarity task in the case of news articles. Our best model achieved a score of 0.511, but shows that there is room for improvement.
%R 10.18653/v1/2022.semeval-1.169
%U https://aclanthology.org/2022.semeval-1.169/
%U https://doi.org/10.18653/v1/2022.semeval-1.169
%P 1196-1201
Markdown (Informal)
[Team dina at SemEval-2022 Task 8: Pre-trained Language Models as Baselines for Semantic Similarity](https://aclanthology.org/2022.semeval-1.169/) (Pisarevskaya & Zubiaga, SemEval 2022)
ACL