@article{sabo-etal-2021-revisiting,
title = "Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes",
author = "Sabo, Ofer and
Elazar, Yanai and
Goldberg, Yoav and
Dagan, Ido",
editor = "Roark, Brian and
Nenkova, Ani",
journal = "Transactions of the Association for Computational Linguistics",
volume = "9",
year = "2021",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2021.tacl-1.42",
doi = "10.1162/tacl_a_00392",
pages = "691--706",
abstract = "We explore few-shot learning (FSL) for relation classification (RC). Focusing on the realistic scenario of FSL, in which a test instance might not belong to any of the target categories (none-of-the-above, [NOTA]), we first revisit the recent popular dataset structure for FSL, pointing out its unrealistic data distribution. To remedy this, we propose a novel methodology for deriving more realistic few-shot test data from available datasets for supervised RC, and apply it to the TACRED dataset. This yields a new challenging benchmark for FSL-RC, on which state of the art models show poor performance. Next, we analyze classification schemes within the popular embedding-based nearest-neighbor approach for FSL, with respect to constraints they impose on the embedding space. Triggered by this analysis, we propose a novel classification scheme in which the NOTA category is represented as learned vectors, shown empirically to be an appealing option for FSL.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sabo-etal-2021-revisiting">
<titleInfo>
<title>Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ofer</namePart>
<namePart type="family">Sabo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanai</namePart>
<namePart type="family">Elazar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ido</namePart>
<namePart type="family">Dagan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>We explore few-shot learning (FSL) for relation classification (RC). Focusing on the realistic scenario of FSL, in which a test instance might not belong to any of the target categories (none-of-the-above, [NOTA]), we first revisit the recent popular dataset structure for FSL, pointing out its unrealistic data distribution. To remedy this, we propose a novel methodology for deriving more realistic few-shot test data from available datasets for supervised RC, and apply it to the TACRED dataset. This yields a new challenging benchmark for FSL-RC, on which state of the art models show poor performance. Next, we analyze classification schemes within the popular embedding-based nearest-neighbor approach for FSL, with respect to constraints they impose on the embedding space. Triggered by this analysis, we propose a novel classification scheme in which the NOTA category is represented as learned vectors, shown empirically to be an appealing option for FSL.</abstract>
<identifier type="citekey">sabo-etal-2021-revisiting</identifier>
<identifier type="doi">10.1162/tacl_a_00392</identifier>
<location>
<url>https://aclanthology.org/2021.tacl-1.42</url>
</location>
<part>
<date>2021</date>
<detail type="volume"><number>9</number></detail>
<extent unit="page">
<start>691</start>
<end>706</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes
%A Sabo, Ofer
%A Elazar, Yanai
%A Goldberg, Yoav
%A Dagan, Ido
%J Transactions of the Association for Computational Linguistics
%D 2021
%V 9
%I MIT Press
%C Cambridge, MA
%F sabo-etal-2021-revisiting
%X We explore few-shot learning (FSL) for relation classification (RC). Focusing on the realistic scenario of FSL, in which a test instance might not belong to any of the target categories (none-of-the-above, [NOTA]), we first revisit the recent popular dataset structure for FSL, pointing out its unrealistic data distribution. To remedy this, we propose a novel methodology for deriving more realistic few-shot test data from available datasets for supervised RC, and apply it to the TACRED dataset. This yields a new challenging benchmark for FSL-RC, on which state of the art models show poor performance. Next, we analyze classification schemes within the popular embedding-based nearest-neighbor approach for FSL, with respect to constraints they impose on the embedding space. Triggered by this analysis, we propose a novel classification scheme in which the NOTA category is represented as learned vectors, shown empirically to be an appealing option for FSL.
%R 10.1162/tacl_a_00392
%U https://aclanthology.org/2021.tacl-1.42
%U https://doi.org/10.1162/tacl_a_00392
%P 691-706
Markdown (Informal)
[Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes](https://aclanthology.org/2021.tacl-1.42) (Sabo et al., TACL 2021)
ACL