@inproceedings{yuan-strohmaier-2021-cambridge,
title = "{C}ambridge at {S}em{E}val-2021 Task 2: Neural {W}i{C}-Model with Data Augmentation and Exploration of Representation",
author = "Yuan, Zheng and
Strohmaier, David",
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-1.96/",
doi = "10.18653/v1/2021.semeval-1.96",
pages = "730--737",
abstract = "This paper describes the system of the Cambridge team submitted to the SemEval-2021 shared task on Multilingual and Cross-lingual Word-in-Context Disambiguation. Building on top of a pre-trained masked language model, our system is first pre-trained on out-of-domain data, and then fine-tuned on in-domain data. We demonstrate the effectiveness of the proposed two-step training strategy and the benefits of data augmentation from both existing examples and new resources. We further investigate different representations and show that the addition of distance-based features is helpful in the word-in-context disambiguation task. Our system yields highly competitive results in the cross-lingual track without training on any cross-lingual data; and achieves state-of-the-art results in the multilingual track, ranking first in two languages (Arabic and Russian) and second in French out of 171 submitted systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuan-strohmaier-2021-cambridge">
<titleInfo>
<title>Cambridge at SemEval-2021 Task 2: Neural WiC-Model with Data Augmentation and Exploration of Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Strohmaier</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 describes the system of the Cambridge team submitted to the SemEval-2021 shared task on Multilingual and Cross-lingual Word-in-Context Disambiguation. Building on top of a pre-trained masked language model, our system is first pre-trained on out-of-domain data, and then fine-tuned on in-domain data. We demonstrate the effectiveness of the proposed two-step training strategy and the benefits of data augmentation from both existing examples and new resources. We further investigate different representations and show that the addition of distance-based features is helpful in the word-in-context disambiguation task. Our system yields highly competitive results in the cross-lingual track without training on any cross-lingual data; and achieves state-of-the-art results in the multilingual track, ranking first in two languages (Arabic and Russian) and second in French out of 171 submitted systems.</abstract>
<identifier type="citekey">yuan-strohmaier-2021-cambridge</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.96</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.96/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>730</start>
<end>737</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cambridge at SemEval-2021 Task 2: Neural WiC-Model with Data Augmentation and Exploration of Representation
%A Yuan, Zheng
%A Strohmaier, David
%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 yuan-strohmaier-2021-cambridge
%X This paper describes the system of the Cambridge team submitted to the SemEval-2021 shared task on Multilingual and Cross-lingual Word-in-Context Disambiguation. Building on top of a pre-trained masked language model, our system is first pre-trained on out-of-domain data, and then fine-tuned on in-domain data. We demonstrate the effectiveness of the proposed two-step training strategy and the benefits of data augmentation from both existing examples and new resources. We further investigate different representations and show that the addition of distance-based features is helpful in the word-in-context disambiguation task. Our system yields highly competitive results in the cross-lingual track without training on any cross-lingual data; and achieves state-of-the-art results in the multilingual track, ranking first in two languages (Arabic and Russian) and second in French out of 171 submitted systems.
%R 10.18653/v1/2021.semeval-1.96
%U https://aclanthology.org/2021.semeval-1.96/
%U https://doi.org/10.18653/v1/2021.semeval-1.96
%P 730-737
Markdown (Informal)
[Cambridge at SemEval-2021 Task 2: Neural WiC-Model with Data Augmentation and Exploration of Representation](https://aclanthology.org/2021.semeval-1.96/) (Yuan & Strohmaier, SemEval 2021)
ACL