@inproceedings{gera-etal-2022-zero,
title = "Zero-Shot Text Classification with Self-Training",
author = "Gera, Ariel and
Halfon, Alon and
Shnarch, Eyal and
Perlitz, Yotam and
Ein-Dor, Liat and
Slonim, Noam",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.73",
doi = "10.18653/v1/2022.emnlp-main.73",
pages = "1107--1119",
abstract = "Recent advances in large pretrained language models have increased attention to zero-shot text classification. In particular, models finetuned on natural language inference datasets have been widely adopted as zero-shot classifiers due to their promising results and off-the-shelf availability. However, the fact that such models are unfamiliar with the target task can lead to instability and performance issues. We propose a plug-and-play method to bridge this gap using a simple self-training approach, requiring only the class names along with an unlabeled dataset, and without the need for domain expertise or trial and error. We show that fine-tuning the zero-shot classifier on its most confident predictions leads to significant performance gains across a wide range of text classification tasks, presumably since self-training adapts the zero-shot model to the task at hand.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gera-etal-2022-zero">
<titleInfo>
<title>Zero-Shot Text Classification with Self-Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ariel</namePart>
<namePart type="family">Gera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alon</namePart>
<namePart type="family">Halfon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eyal</namePart>
<namePart type="family">Shnarch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yotam</namePart>
<namePart type="family">Perlitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liat</namePart>
<namePart type="family">Ein-Dor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noam</namePart>
<namePart type="family">Slonim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in large pretrained language models have increased attention to zero-shot text classification. In particular, models finetuned on natural language inference datasets have been widely adopted as zero-shot classifiers due to their promising results and off-the-shelf availability. However, the fact that such models are unfamiliar with the target task can lead to instability and performance issues. We propose a plug-and-play method to bridge this gap using a simple self-training approach, requiring only the class names along with an unlabeled dataset, and without the need for domain expertise or trial and error. We show that fine-tuning the zero-shot classifier on its most confident predictions leads to significant performance gains across a wide range of text classification tasks, presumably since self-training adapts the zero-shot model to the task at hand.</abstract>
<identifier type="citekey">gera-etal-2022-zero</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.73</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.73</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1107</start>
<end>1119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-Shot Text Classification with Self-Training
%A Gera, Ariel
%A Halfon, Alon
%A Shnarch, Eyal
%A Perlitz, Yotam
%A Ein-Dor, Liat
%A Slonim, Noam
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F gera-etal-2022-zero
%X Recent advances in large pretrained language models have increased attention to zero-shot text classification. In particular, models finetuned on natural language inference datasets have been widely adopted as zero-shot classifiers due to their promising results and off-the-shelf availability. However, the fact that such models are unfamiliar with the target task can lead to instability and performance issues. We propose a plug-and-play method to bridge this gap using a simple self-training approach, requiring only the class names along with an unlabeled dataset, and without the need for domain expertise or trial and error. We show that fine-tuning the zero-shot classifier on its most confident predictions leads to significant performance gains across a wide range of text classification tasks, presumably since self-training adapts the zero-shot model to the task at hand.
%R 10.18653/v1/2022.emnlp-main.73
%U https://aclanthology.org/2022.emnlp-main.73
%U https://doi.org/10.18653/v1/2022.emnlp-main.73
%P 1107-1119
Markdown (Informal)
[Zero-Shot Text Classification with Self-Training](https://aclanthology.org/2022.emnlp-main.73) (Gera et al., EMNLP 2022)
ACL
- Ariel Gera, Alon Halfon, Eyal Shnarch, Yotam Perlitz, Liat Ein-Dor, and Noam Slonim. 2022. Zero-Shot Text Classification with Self-Training. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1107–1119, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.