@inproceedings{chen-etal-2023-learning,
title = "Learning In-context Learning for Named Entity Recognition",
author = "Chen, Jiawei and
Lu, Yaojie and
Lin, Hongyu and
Lou, Jie and
Jia, Wei and
Dai, Dai and
Wu, Hua and
Cao, Boxi and
Han, Xianpei and
Sun, Le",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.764",
doi = "10.18653/v1/2023.acl-long.764",
pages = "13661--13675",
abstract = "Named entity recognition in real-world applications suffers from the diversity of entity types, the emergence of new entity types, and the lack of high-quality annotations. To address the above problems, this paper proposes an in-context learning-based NER approach, which can effectively inject in-context NER ability into PLMs and recognize entities of novel types on-the-fly using only a few demonstrative instances. Specifically, we model PLMs as a meta-function Lambda{\_}instruction, demonstrations, text.M, and a new entity extractor can be implicitly constructed by applying new instruction and demonstrations to PLMs, i.e., (Lambda . M) (instruction, demonstrations) -{\textgreater}F where F will be a new entity extractor F: text -{\textgreater} entities. To inject the above in-context NER ability into PLMs, we propose a meta-function pre-training algorithm, which pre-trains PLMs by comparing the (instruction, demonstration)-initialized extractor with a surrogate golden extractor. Experimental results on 4 few-shot NER datasets show that our method can effectively inject in-context NER ability into PLMs and significantly outperforms the PLMs+fine-tuning counterparts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-learning">
<titleInfo>
<title>Learning In-context Learning for Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaojie</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Lou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dai</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boxi</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="family">Sun</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>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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>Named entity recognition in real-world applications suffers from the diversity of entity types, the emergence of new entity types, and the lack of high-quality annotations. To address the above problems, this paper proposes an in-context learning-based NER approach, which can effectively inject in-context NER ability into PLMs and recognize entities of novel types on-the-fly using only a few demonstrative instances. Specifically, we model PLMs as a meta-function Lambda_instruction, demonstrations, text.M, and a new entity extractor can be implicitly constructed by applying new instruction and demonstrations to PLMs, i.e., (Lambda . M) (instruction, demonstrations) -\textgreaterF where F will be a new entity extractor F: text -\textgreater entities. To inject the above in-context NER ability into PLMs, we propose a meta-function pre-training algorithm, which pre-trains PLMs by comparing the (instruction, demonstration)-initialized extractor with a surrogate golden extractor. Experimental results on 4 few-shot NER datasets show that our method can effectively inject in-context NER ability into PLMs and significantly outperforms the PLMs+fine-tuning counterparts.</abstract>
<identifier type="citekey">chen-etal-2023-learning</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.764</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.764</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>13661</start>
<end>13675</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning In-context Learning for Named Entity Recognition
%A Chen, Jiawei
%A Lu, Yaojie
%A Lin, Hongyu
%A Lou, Jie
%A Jia, Wei
%A Dai, Dai
%A Wu, Hua
%A Cao, Boxi
%A Han, Xianpei
%A Sun, Le
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F chen-etal-2023-learning
%X Named entity recognition in real-world applications suffers from the diversity of entity types, the emergence of new entity types, and the lack of high-quality annotations. To address the above problems, this paper proposes an in-context learning-based NER approach, which can effectively inject in-context NER ability into PLMs and recognize entities of novel types on-the-fly using only a few demonstrative instances. Specifically, we model PLMs as a meta-function Lambda_instruction, demonstrations, text.M, and a new entity extractor can be implicitly constructed by applying new instruction and demonstrations to PLMs, i.e., (Lambda . M) (instruction, demonstrations) -\textgreaterF where F will be a new entity extractor F: text -\textgreater entities. To inject the above in-context NER ability into PLMs, we propose a meta-function pre-training algorithm, which pre-trains PLMs by comparing the (instruction, demonstration)-initialized extractor with a surrogate golden extractor. Experimental results on 4 few-shot NER datasets show that our method can effectively inject in-context NER ability into PLMs and significantly outperforms the PLMs+fine-tuning counterparts.
%R 10.18653/v1/2023.acl-long.764
%U https://aclanthology.org/2023.acl-long.764
%U https://doi.org/10.18653/v1/2023.acl-long.764
%P 13661-13675
Markdown (Informal)
[Learning In-context Learning for Named Entity Recognition](https://aclanthology.org/2023.acl-long.764) (Chen et al., ACL 2023)
ACL
- Jiawei Chen, Yaojie Lu, Hongyu Lin, Jie Lou, Wei Jia, Dai Dai, Hua Wu, Boxi Cao, Xianpei Han, and Le Sun. 2023. Learning In-context Learning for Named Entity Recognition. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13661–13675, Toronto, Canada. Association for Computational Linguistics.