@inproceedings{jin-etal-2023-alignment,
title = "Alignment Precedes Fusion: Open-Vocabulary Named Entity Recognition as Context-Type Semantic Matching",
author = "Jin, Zhuoran and
Cao, Pengfei and
He, Zhitao and
Chen, Yubo and
Liu, Kang and
Zhao, Jun",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.974/",
doi = "10.18653/v1/2023.findings-emnlp.974",
pages = "14616--14637",
abstract = "Despite the significant progress in developing named entity recognition models, scaling to novel-emerging types still remains challenging in real-world scenarios. Continual learning and zero-shot learning approaches have been explored to handle novel-emerging types with less human supervision, but they have not been as successfully adopted as supervised approaches. Meanwhile, humans possess a much larger vocabulary size than these approaches and have the ability to learn the alignment between entities and concepts effortlessly through natural supervision. In this paper, we consider a more realistic and challenging setting called open-vocabulary named entity recognition (OVNER) to imitate human-level ability. OVNER aims to recognize entities in novel types by their textual names or descriptions. Specifically, we formulate OVNER as a semantic matching task and propose a novel and scalable two-stage method called Context-Type SemAntiC Alignment and FusiOn (CACAO). In the pre-training stage, we adopt Dual-Encoder for context-type semantic alignment and pre-train Dual-Encoder on 80M context-type pairs which are easily accessible through natural supervision. In the fine-tuning stage, we use Cross-Encoder for context-type semantic fusion and fine-tune Cross-Encoder on base types with human supervision. Experimental results show that our method outperforms the previous state-of-the-art methods on three challenging OVNER benchmarks by 9.7{\%}, 9.5{\%}, and 1.8{\%} F1-score of novel types. Moreover, CACAO also demonstrates its flexible transfer ability in cross-domain NER."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-etal-2023-alignment">
<titleInfo>
<title>Alignment Precedes Fusion: Open-Vocabulary Named Entity Recognition as Context-Type Semantic Matching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhuoran</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengfei</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhitao</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite the significant progress in developing named entity recognition models, scaling to novel-emerging types still remains challenging in real-world scenarios. Continual learning and zero-shot learning approaches have been explored to handle novel-emerging types with less human supervision, but they have not been as successfully adopted as supervised approaches. Meanwhile, humans possess a much larger vocabulary size than these approaches and have the ability to learn the alignment between entities and concepts effortlessly through natural supervision. In this paper, we consider a more realistic and challenging setting called open-vocabulary named entity recognition (OVNER) to imitate human-level ability. OVNER aims to recognize entities in novel types by their textual names or descriptions. Specifically, we formulate OVNER as a semantic matching task and propose a novel and scalable two-stage method called Context-Type SemAntiC Alignment and FusiOn (CACAO). In the pre-training stage, we adopt Dual-Encoder for context-type semantic alignment and pre-train Dual-Encoder on 80M context-type pairs which are easily accessible through natural supervision. In the fine-tuning stage, we use Cross-Encoder for context-type semantic fusion and fine-tune Cross-Encoder on base types with human supervision. Experimental results show that our method outperforms the previous state-of-the-art methods on three challenging OVNER benchmarks by 9.7%, 9.5%, and 1.8% F1-score of novel types. Moreover, CACAO also demonstrates its flexible transfer ability in cross-domain NER.</abstract>
<identifier type="citekey">jin-etal-2023-alignment</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.974</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.974/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>14616</start>
<end>14637</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Alignment Precedes Fusion: Open-Vocabulary Named Entity Recognition as Context-Type Semantic Matching
%A Jin, Zhuoran
%A Cao, Pengfei
%A He, Zhitao
%A Chen, Yubo
%A Liu, Kang
%A Zhao, Jun
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F jin-etal-2023-alignment
%X Despite the significant progress in developing named entity recognition models, scaling to novel-emerging types still remains challenging in real-world scenarios. Continual learning and zero-shot learning approaches have been explored to handle novel-emerging types with less human supervision, but they have not been as successfully adopted as supervised approaches. Meanwhile, humans possess a much larger vocabulary size than these approaches and have the ability to learn the alignment between entities and concepts effortlessly through natural supervision. In this paper, we consider a more realistic and challenging setting called open-vocabulary named entity recognition (OVNER) to imitate human-level ability. OVNER aims to recognize entities in novel types by their textual names or descriptions. Specifically, we formulate OVNER as a semantic matching task and propose a novel and scalable two-stage method called Context-Type SemAntiC Alignment and FusiOn (CACAO). In the pre-training stage, we adopt Dual-Encoder for context-type semantic alignment and pre-train Dual-Encoder on 80M context-type pairs which are easily accessible through natural supervision. In the fine-tuning stage, we use Cross-Encoder for context-type semantic fusion and fine-tune Cross-Encoder on base types with human supervision. Experimental results show that our method outperforms the previous state-of-the-art methods on three challenging OVNER benchmarks by 9.7%, 9.5%, and 1.8% F1-score of novel types. Moreover, CACAO also demonstrates its flexible transfer ability in cross-domain NER.
%R 10.18653/v1/2023.findings-emnlp.974
%U https://aclanthology.org/2023.findings-emnlp.974/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.974
%P 14616-14637
Markdown (Informal)
[Alignment Precedes Fusion: Open-Vocabulary Named Entity Recognition as Context-Type Semantic Matching](https://aclanthology.org/2023.findings-emnlp.974/) (Jin et al., Findings 2023)
ACL