@inproceedings{babvey-etal-2020-pheonix,
title = "Pheonix at {S}em{E}val-2020 Task 5: Masking the Labels Lubricates Models for Sequence Labeling",
author = "Babvey, Pouria and
Borrelli, Dario and
Zhao, Yutong and
Lipizzi, Carlo",
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-1.88/",
doi = "10.18653/v1/2020.semeval-1.88",
pages = "677--682",
abstract = "This paper presents the deep-learning model that is submitted to the SemEval-2020 Task 5 competition: {\textquotedblleft}Detecting Counterfactuals{\textquotedblright}. We participated in both Subtask1 and Subtask2. The model proposed in this paper ranked 2nd in Subtask2 {\textquotedblleft}Detecting antecedent and consequence{\textquotedblright}. Our model approaches the task as a sequence labeling. The architecture is built on top of BERT, and a multi-head attention layer with label masking is used to benefit from the mutual information between nearby labels. Also, for prediction, a multi-stage algorithm is used in which the model finalize some predictions with higher certainty in each step and use them in the following. Our results show that masking the labels not only is an efficient regularization method but also improves the accuracy of the model compared with other alternatives like CRF. Label masking can be used as a regularization method in sequence labeling. Also, it improves the performance of the model by learning the specific patterns in the target variable."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="babvey-etal-2020-pheonix">
<titleInfo>
<title>Pheonix at SemEval-2020 Task 5: Masking the Labels Lubricates Models for Sequence Labeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pouria</namePart>
<namePart type="family">Babvey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dario</namePart>
<namePart type="family">Borrelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutong</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlo</namePart>
<namePart type="family">Lipizzi</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 presents the deep-learning model that is submitted to the SemEval-2020 Task 5 competition: “Detecting Counterfactuals”. We participated in both Subtask1 and Subtask2. The model proposed in this paper ranked 2nd in Subtask2 “Detecting antecedent and consequence”. Our model approaches the task as a sequence labeling. The architecture is built on top of BERT, and a multi-head attention layer with label masking is used to benefit from the mutual information between nearby labels. Also, for prediction, a multi-stage algorithm is used in which the model finalize some predictions with higher certainty in each step and use them in the following. Our results show that masking the labels not only is an efficient regularization method but also improves the accuracy of the model compared with other alternatives like CRF. Label masking can be used as a regularization method in sequence labeling. Also, it improves the performance of the model by learning the specific patterns in the target variable.</abstract>
<identifier type="citekey">babvey-etal-2020-pheonix</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.88</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.88/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>677</start>
<end>682</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pheonix at SemEval-2020 Task 5: Masking the Labels Lubricates Models for Sequence Labeling
%A Babvey, Pouria
%A Borrelli, Dario
%A Zhao, Yutong
%A Lipizzi, Carlo
%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 babvey-etal-2020-pheonix
%X This paper presents the deep-learning model that is submitted to the SemEval-2020 Task 5 competition: “Detecting Counterfactuals”. We participated in both Subtask1 and Subtask2. The model proposed in this paper ranked 2nd in Subtask2 “Detecting antecedent and consequence”. Our model approaches the task as a sequence labeling. The architecture is built on top of BERT, and a multi-head attention layer with label masking is used to benefit from the mutual information between nearby labels. Also, for prediction, a multi-stage algorithm is used in which the model finalize some predictions with higher certainty in each step and use them in the following. Our results show that masking the labels not only is an efficient regularization method but also improves the accuracy of the model compared with other alternatives like CRF. Label masking can be used as a regularization method in sequence labeling. Also, it improves the performance of the model by learning the specific patterns in the target variable.
%R 10.18653/v1/2020.semeval-1.88
%U https://aclanthology.org/2020.semeval-1.88/
%U https://doi.org/10.18653/v1/2020.semeval-1.88
%P 677-682
Markdown (Informal)
[Pheonix at SemEval-2020 Task 5: Masking the Labels Lubricates Models for Sequence Labeling](https://aclanthology.org/2020.semeval-1.88/) (Babvey et al., SemEval 2020)
ACL