@inproceedings{bujel-etal-2021-zero,
title = "Zero-shot Sequence Labeling for Transformer-based Sentence Classifiers",
author = "Bujel, Kamil and
Yannakoudakis, Helen and
Rei, Marek",
editor = "Rogers, Anna and
Calixto, Iacer and
Vuli{\'c}, Ivan and
Saphra, Naomi and
Kassner, Nora and
Camburu, Oana-Maria and
Bansal, Trapit and
Shwartz, Vered",
booktitle = "Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.repl4nlp-1.20",
doi = "10.18653/v1/2021.repl4nlp-1.20",
pages = "195--205",
abstract = "We investigate how sentence-level transformers can be modified into effective sequence labelers at the token level without any direct supervision. Existing approaches to zero-shot sequence labeling do not perform well when applied on transformer-based architectures. As transformers contain multiple layers of multi-head self-attention, information in the sentence gets distributed between many tokens, negatively affecting zero-shot token-level performance. We find that a soft attention module which explicitly encourages sharpness of attention weights can significantly outperform existing methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bujel-etal-2021-zero">
<titleInfo>
<title>Zero-shot Sequence Labeling for Transformer-based Sentence Classifiers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kamil</namePart>
<namePart type="family">Bujel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Rei</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 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iacer</namePart>
<namePart type="family">Calixto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naomi</namePart>
<namePart type="family">Saphra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Kassner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana-Maria</namePart>
<namePart type="family">Camburu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trapit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</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>We investigate how sentence-level transformers can be modified into effective sequence labelers at the token level without any direct supervision. Existing approaches to zero-shot sequence labeling do not perform well when applied on transformer-based architectures. As transformers contain multiple layers of multi-head self-attention, information in the sentence gets distributed between many tokens, negatively affecting zero-shot token-level performance. We find that a soft attention module which explicitly encourages sharpness of attention weights can significantly outperform existing methods.</abstract>
<identifier type="citekey">bujel-etal-2021-zero</identifier>
<identifier type="doi">10.18653/v1/2021.repl4nlp-1.20</identifier>
<location>
<url>https://aclanthology.org/2021.repl4nlp-1.20</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>195</start>
<end>205</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-shot Sequence Labeling for Transformer-based Sentence Classifiers
%A Bujel, Kamil
%A Yannakoudakis, Helen
%A Rei, Marek
%Y Rogers, Anna
%Y Calixto, Iacer
%Y Vulić, Ivan
%Y Saphra, Naomi
%Y Kassner, Nora
%Y Camburu, Oana-Maria
%Y Bansal, Trapit
%Y Shwartz, Vered
%S Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F bujel-etal-2021-zero
%X We investigate how sentence-level transformers can be modified into effective sequence labelers at the token level without any direct supervision. Existing approaches to zero-shot sequence labeling do not perform well when applied on transformer-based architectures. As transformers contain multiple layers of multi-head self-attention, information in the sentence gets distributed between many tokens, negatively affecting zero-shot token-level performance. We find that a soft attention module which explicitly encourages sharpness of attention weights can significantly outperform existing methods.
%R 10.18653/v1/2021.repl4nlp-1.20
%U https://aclanthology.org/2021.repl4nlp-1.20
%U https://doi.org/10.18653/v1/2021.repl4nlp-1.20
%P 195-205
Markdown (Informal)
[Zero-shot Sequence Labeling for Transformer-based Sentence Classifiers](https://aclanthology.org/2021.repl4nlp-1.20) (Bujel et al., RepL4NLP 2021)
ACL