@inproceedings{wang-etal-2022-spanproto,
title = "{S}pan{P}roto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition",
author = "Wang, Jianing and
Wang, Chengyu and
Tan, Chuanqi and
Qiu, Minghui and
Huang, Songfang and
Huang, Jun and
Gao, Ming",
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.227",
doi = "10.18653/v1/2022.emnlp-main.227",
pages = "3466--3476",
abstract = "Few-shot Named Entity Recognition (NER) aims to identify named entities with very little annotated data. Previous methods solve this problem based on token-wise classification, which ignores the information of entity boundaries, and inevitably the performance is affected by the massive non-entity tokens. To this end, we propose a seminal span-based prototypical network (SpanProto) that tackles few-shot NER via a two-stage approach, including span extraction and mention classification. In the span extraction stage, we transform the sequential tags into a global boundary matrix, enabling the model to focus on the explicit boundary information. For mention classification, we leverage prototypical learning to capture the semantic representations for each labeled span and make the model better adapt to novel-class entities. To further improve the model performance, we split out the false positives generated by the span extractor but not labeled in the current episode set, and then present a margin-based loss to separate them from each prototype region. Experiments over multiple benchmarks demonstrate that our model outperforms strong baselines by a large margin.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-spanproto">
<titleInfo>
<title>SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuanqi</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghui</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songfang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Gao</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>Few-shot Named Entity Recognition (NER) aims to identify named entities with very little annotated data. Previous methods solve this problem based on token-wise classification, which ignores the information of entity boundaries, and inevitably the performance is affected by the massive non-entity tokens. To this end, we propose a seminal span-based prototypical network (SpanProto) that tackles few-shot NER via a two-stage approach, including span extraction and mention classification. In the span extraction stage, we transform the sequential tags into a global boundary matrix, enabling the model to focus on the explicit boundary information. For mention classification, we leverage prototypical learning to capture the semantic representations for each labeled span and make the model better adapt to novel-class entities. To further improve the model performance, we split out the false positives generated by the span extractor but not labeled in the current episode set, and then present a margin-based loss to separate them from each prototype region. Experiments over multiple benchmarks demonstrate that our model outperforms strong baselines by a large margin.</abstract>
<identifier type="citekey">wang-etal-2022-spanproto</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.227</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.227</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>3466</start>
<end>3476</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition
%A Wang, Jianing
%A Wang, Chengyu
%A Tan, Chuanqi
%A Qiu, Minghui
%A Huang, Songfang
%A Huang, Jun
%A Gao, Ming
%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 wang-etal-2022-spanproto
%X Few-shot Named Entity Recognition (NER) aims to identify named entities with very little annotated data. Previous methods solve this problem based on token-wise classification, which ignores the information of entity boundaries, and inevitably the performance is affected by the massive non-entity tokens. To this end, we propose a seminal span-based prototypical network (SpanProto) that tackles few-shot NER via a two-stage approach, including span extraction and mention classification. In the span extraction stage, we transform the sequential tags into a global boundary matrix, enabling the model to focus on the explicit boundary information. For mention classification, we leverage prototypical learning to capture the semantic representations for each labeled span and make the model better adapt to novel-class entities. To further improve the model performance, we split out the false positives generated by the span extractor but not labeled in the current episode set, and then present a margin-based loss to separate them from each prototype region. Experiments over multiple benchmarks demonstrate that our model outperforms strong baselines by a large margin.
%R 10.18653/v1/2022.emnlp-main.227
%U https://aclanthology.org/2022.emnlp-main.227
%U https://doi.org/10.18653/v1/2022.emnlp-main.227
%P 3466-3476
Markdown (Informal)
[SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition](https://aclanthology.org/2022.emnlp-main.227) (Wang et al., EMNLP 2022)
ACL