@inproceedings{huang-etal-2020-ernie,
title = "{ERNIE} at {S}em{E}val-2020 Task 10: Learning Word Emphasis Selection by Pre-trained Language Model",
author = "Huang, Zhengjie and
Feng, Shikun and
Su, Weiyue and
Chen, Xuyi and
Wang, Shuohuan and
Liu, Jiaxiang and
Ouyang, Xuan and
Sun, Yu",
editor = "Herbelot, Aurelie and
Zhu, Xiaodan and
Palmer, Alexis and
Schneider, Nathan and
May, Jonathan and
Shutova, Ekaterina",
booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
month = dec,
year = "2020",
address = "Barcelona (online)",
publisher = "International Committee for Computational Linguistics",
url = "https://aclanthology.org/2020.semeval-1.190",
doi = "10.18653/v1/2020.semeval-1.190",
pages = "1456--1461",
abstract = "This paper describes the system designed by ERNIE Team which achieved the first place in SemEval-2020 Task 10: Emphasis Selection For Written Text in Visual Media. Given a sentence, we are asked to find out the most important words as the suggestion for automated design. We leverage the unsupervised pre-training model and finetune these models on our task. After our investigation, we found that the following models achieved an excellent performance in this task: ERNIE 2.0, XLM-ROBERTA, ROBERTA and ALBERT. We combine a pointwise regression loss and a pairwise ranking loss which is more close to the final Match m metric to finetune our models. And we also find that additional feature engineering and data augmentation can help improve the performance. Our best model achieves the highest score of 0.823 and ranks first for all kinds of metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2020-ernie">
<titleInfo>
<title>ERNIE at SemEval-2020 Task 10: Learning Word Emphasis Selection by Pre-trained Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhengjie</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikun</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiyue</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuyi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuohuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxiang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourteenth Workshop on Semantic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</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">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the system designed by ERNIE Team which achieved the first place in SemEval-2020 Task 10: Emphasis Selection For Written Text in Visual Media. Given a sentence, we are asked to find out the most important words as the suggestion for automated design. We leverage the unsupervised pre-training model and finetune these models on our task. After our investigation, we found that the following models achieved an excellent performance in this task: ERNIE 2.0, XLM-ROBERTA, ROBERTA and ALBERT. We combine a pointwise regression loss and a pairwise ranking loss which is more close to the final Match m metric to finetune our models. And we also find that additional feature engineering and data augmentation can help improve the performance. Our best model achieves the highest score of 0.823 and ranks first for all kinds of metrics.</abstract>
<identifier type="citekey">huang-etal-2020-ernie</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.190</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.190</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1456</start>
<end>1461</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ERNIE at SemEval-2020 Task 10: Learning Word Emphasis Selection by Pre-trained Language Model
%A Huang, Zhengjie
%A Feng, Shikun
%A Su, Weiyue
%A Chen, Xuyi
%A Wang, Shuohuan
%A Liu, Jiaxiang
%A Ouyang, Xuan
%A Sun, Yu
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y May, Jonathan
%Y Shutova, Ekaterina
%S Proceedings of the Fourteenth Workshop on Semantic Evaluation
%D 2020
%8 December
%I International Committee for Computational Linguistics
%C Barcelona (online)
%F huang-etal-2020-ernie
%X This paper describes the system designed by ERNIE Team which achieved the first place in SemEval-2020 Task 10: Emphasis Selection For Written Text in Visual Media. Given a sentence, we are asked to find out the most important words as the suggestion for automated design. We leverage the unsupervised pre-training model and finetune these models on our task. After our investigation, we found that the following models achieved an excellent performance in this task: ERNIE 2.0, XLM-ROBERTA, ROBERTA and ALBERT. We combine a pointwise regression loss and a pairwise ranking loss which is more close to the final Match m metric to finetune our models. And we also find that additional feature engineering and data augmentation can help improve the performance. Our best model achieves the highest score of 0.823 and ranks first for all kinds of metrics.
%R 10.18653/v1/2020.semeval-1.190
%U https://aclanthology.org/2020.semeval-1.190
%U https://doi.org/10.18653/v1/2020.semeval-1.190
%P 1456-1461
Markdown (Informal)
[ERNIE at SemEval-2020 Task 10: Learning Word Emphasis Selection by Pre-trained Language Model](https://aclanthology.org/2020.semeval-1.190) (Huang et al., SemEval 2020)
ACL