@inproceedings{xie-etal-2021-pali,
title = "{PALI} at {S}em{E}val-2021 Task 2: Fine-Tune {XLM}-{R}o{BERT}a for Word in Context Disambiguation",
author = "Xie, Shuyi and
Ma, Jian and
Yang, Haiqin and
Jiang, Lianxin and
Mo, Yang and
Shen, Jianping",
editor = "Palmer, Alexis and
Schneider, Nathan and
Schluter, Natalie and
Emerson, Guy and
Herbelot, Aurelie and
Zhu, Xiaodan",
booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.semeval-1.93",
doi = "10.18653/v1/2021.semeval-1.93",
pages = "713--718",
abstract = "This paper presents the PALI team{'}s winning system for SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation. We fine-tune XLM-RoBERTa model to solve the task of word in context disambiguation, i.e., to determine whether the target word in the two contexts contains the same meaning or not. In implementation, we first specifically design an input tag to emphasize the target word in the contexts. Second, we construct a new vector on the fine-tuned embeddings from XLM-RoBERTa and feed it to a fully-connected network to output the probability of whether the target word in the context has the same meaning or not. The new vector is attained by concatenating the embedding of the [CLS] token and the embeddings of the target word in the contexts. In training, we explore several tricks, such as the Ranger optimizer, data augmentation, and adversarial training, to improve the model prediction. Consequently, we attain the first place in all four cross-lingual tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xie-etal-2021-pali">
<titleInfo>
<title>PALI at SemEval-2021 Task 2: Fine-Tune XLM-RoBERTa for Word in Context Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuyi</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiqin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lianxin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Mo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianping</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)</title>
</titleInfo>
<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">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the PALI team’s winning system for SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation. We fine-tune XLM-RoBERTa model to solve the task of word in context disambiguation, i.e., to determine whether the target word in the two contexts contains the same meaning or not. In implementation, we first specifically design an input tag to emphasize the target word in the contexts. Second, we construct a new vector on the fine-tuned embeddings from XLM-RoBERTa and feed it to a fully-connected network to output the probability of whether the target word in the context has the same meaning or not. The new vector is attained by concatenating the embedding of the [CLS] token and the embeddings of the target word in the contexts. In training, we explore several tricks, such as the Ranger optimizer, data augmentation, and adversarial training, to improve the model prediction. Consequently, we attain the first place in all four cross-lingual tasks.</abstract>
<identifier type="citekey">xie-etal-2021-pali</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.93</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.93</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>713</start>
<end>718</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PALI at SemEval-2021 Task 2: Fine-Tune XLM-RoBERTa for Word in Context Disambiguation
%A Xie, Shuyi
%A Ma, Jian
%A Yang, Haiqin
%A Jiang, Lianxin
%A Mo, Yang
%A Shen, Jianping
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Schluter, Natalie
%Y Emerson, Guy
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%S Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F xie-etal-2021-pali
%X This paper presents the PALI team’s winning system for SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation. We fine-tune XLM-RoBERTa model to solve the task of word in context disambiguation, i.e., to determine whether the target word in the two contexts contains the same meaning or not. In implementation, we first specifically design an input tag to emphasize the target word in the contexts. Second, we construct a new vector on the fine-tuned embeddings from XLM-RoBERTa and feed it to a fully-connected network to output the probability of whether the target word in the context has the same meaning or not. The new vector is attained by concatenating the embedding of the [CLS] token and the embeddings of the target word in the contexts. In training, we explore several tricks, such as the Ranger optimizer, data augmentation, and adversarial training, to improve the model prediction. Consequently, we attain the first place in all four cross-lingual tasks.
%R 10.18653/v1/2021.semeval-1.93
%U https://aclanthology.org/2021.semeval-1.93
%U https://doi.org/10.18653/v1/2021.semeval-1.93
%P 713-718
Markdown (Informal)
[PALI at SemEval-2021 Task 2: Fine-Tune XLM-RoBERTa for Word in Context Disambiguation](https://aclanthology.org/2021.semeval-1.93) (Xie et al., SemEval 2021)
ACL