@inproceedings{chen-etal-2023-prompt,
title = "Prompt-Based Metric Learning for Few-Shot {NER}",
author = "Chen, Yanru and
Zheng, Yanan and
Yang, Zhilin",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.451/",
doi = "10.18653/v1/2023.findings-acl.451",
pages = "7199--7212",
abstract = "Few-shot named entity recognition (NER) targets generalizing to unseen labels and/or domains with few labeled examples. Existing metric learning methods compute token-level similarities between query and support sets, but are not able to fully incorporate label semantics into modeling. To address this issue, we propose a simple method to largely improve metric learning for NER: 1) multiple prompt schemas are designed to enhance label semantics; 2) we propose a novel architecture to effectively combine multiple prompt-based representations. Empirically, our method achieves new state-of-the-art (SOTA) results under 16 of the 18 considered settings, substantially outperforming the previous SOTA by an average of 9.12{\%} and a maximum of 34.51{\%} in relative gains of micro F1."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-prompt">
<titleInfo>
<title>Prompt-Based Metric Learning for Few-Shot NER</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanru</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanan</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhilin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</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">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Few-shot named entity recognition (NER) targets generalizing to unseen labels and/or domains with few labeled examples. Existing metric learning methods compute token-level similarities between query and support sets, but are not able to fully incorporate label semantics into modeling. To address this issue, we propose a simple method to largely improve metric learning for NER: 1) multiple prompt schemas are designed to enhance label semantics; 2) we propose a novel architecture to effectively combine multiple prompt-based representations. Empirically, our method achieves new state-of-the-art (SOTA) results under 16 of the 18 considered settings, substantially outperforming the previous SOTA by an average of 9.12% and a maximum of 34.51% in relative gains of micro F1.</abstract>
<identifier type="citekey">chen-etal-2023-prompt</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.451</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.451/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>7199</start>
<end>7212</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Prompt-Based Metric Learning for Few-Shot NER
%A Chen, Yanru
%A Zheng, Yanan
%A Yang, Zhilin
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F chen-etal-2023-prompt
%X Few-shot named entity recognition (NER) targets generalizing to unseen labels and/or domains with few labeled examples. Existing metric learning methods compute token-level similarities between query and support sets, but are not able to fully incorporate label semantics into modeling. To address this issue, we propose a simple method to largely improve metric learning for NER: 1) multiple prompt schemas are designed to enhance label semantics; 2) we propose a novel architecture to effectively combine multiple prompt-based representations. Empirically, our method achieves new state-of-the-art (SOTA) results under 16 of the 18 considered settings, substantially outperforming the previous SOTA by an average of 9.12% and a maximum of 34.51% in relative gains of micro F1.
%R 10.18653/v1/2023.findings-acl.451
%U https://aclanthology.org/2023.findings-acl.451/
%U https://doi.org/10.18653/v1/2023.findings-acl.451
%P 7199-7212
Markdown (Informal)
[Prompt-Based Metric Learning for Few-Shot NER](https://aclanthology.org/2023.findings-acl.451/) (Chen et al., Findings 2023)
ACL
- Yanru Chen, Yanan Zheng, and Zhilin Yang. 2023. Prompt-Based Metric Learning for Few-Shot NER. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7199–7212, Toronto, Canada. Association for Computational Linguistics.