@inproceedings{chittilla-khalil-2022-huaams,
title = "{H}ua{AMS} at {S}em{E}val-2022 Task 8: Combining Translation and Domain Pre-training for Cross-lingual News Article Similarity",
author = "Chittilla, Sai Sandeep Sharma and
Khalil, Talaat",
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-1.162/",
doi = "10.18653/v1/2022.semeval-1.162",
pages = "1151--1156",
abstract = "This paper describes our submission to SemEval-2022 Multilingual News Article Similarity task. We experiment with different approaches that utilize a pre-trained language model fitted with a regression head to predict similarity scores for a given pair of news articles. Our best performing systems include 2 key steps: 1) pre-training with in-domain data 2) training data enrichment through machine translation. Our final submission is an ensemble of predictions from our top systems. While we show the significance of pre-training and augmentation, we believe the issue of language coverage calls for more attention."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chittilla-khalil-2022-huaams">
<titleInfo>
<title>HuaAMS at SemEval-2022 Task 8: Combining Translation and Domain Pre-training for Cross-lingual News Article Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Sandeep</namePart>
<namePart type="given">Sharma</namePart>
<namePart type="family">Chittilla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Talaat</namePart>
<namePart type="family">Khalil</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 submission to SemEval-2022 Multilingual News Article Similarity task. We experiment with different approaches that utilize a pre-trained language model fitted with a regression head to predict similarity scores for a given pair of news articles. Our best performing systems include 2 key steps: 1) pre-training with in-domain data 2) training data enrichment through machine translation. Our final submission is an ensemble of predictions from our top systems. While we show the significance of pre-training and augmentation, we believe the issue of language coverage calls for more attention.</abstract>
<identifier type="citekey">chittilla-khalil-2022-huaams</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.162</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.162/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1151</start>
<end>1156</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HuaAMS at SemEval-2022 Task 8: Combining Translation and Domain Pre-training for Cross-lingual News Article Similarity
%A Chittilla, Sai Sandeep Sharma
%A Khalil, Talaat
%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 chittilla-khalil-2022-huaams
%X This paper describes our submission to SemEval-2022 Multilingual News Article Similarity task. We experiment with different approaches that utilize a pre-trained language model fitted with a regression head to predict similarity scores for a given pair of news articles. Our best performing systems include 2 key steps: 1) pre-training with in-domain data 2) training data enrichment through machine translation. Our final submission is an ensemble of predictions from our top systems. While we show the significance of pre-training and augmentation, we believe the issue of language coverage calls for more attention.
%R 10.18653/v1/2022.semeval-1.162
%U https://aclanthology.org/2022.semeval-1.162/
%U https://doi.org/10.18653/v1/2022.semeval-1.162
%P 1151-1156
Markdown (Informal)
[HuaAMS at SemEval-2022 Task 8: Combining Translation and Domain Pre-training for Cross-lingual News Article Similarity](https://aclanthology.org/2022.semeval-1.162/) (Chittilla & Khalil, SemEval 2022)
ACL