@inproceedings{mengge-etal-2020-coarse,
title = "{C}oarse-to-{F}ine {P}re-training for {N}amed {E}ntity {R}ecognition",
author = "Mengge, Xue and
Yu, Bowen and
Zhang, Zhenyu and
Liu, Tingwen and
Zhang, Yue and
Wang, Bin",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.514",
doi = "10.18653/v1/2020.emnlp-main.514",
pages = "6345--6354",
abstract = "More recently, Named Entity Recognition hasachieved great advances aided by pre-trainingapproaches such as BERT. However, currentpre-training techniques focus on building lan-guage modeling objectives to learn a gen-eral representation, ignoring the named entity-related knowledge. To this end, we proposea NER-specific pre-training framework to in-ject coarse-to-fine automatically mined entityknowledge into pre-trained models. Specifi-cally, we first warm-up the model via an en-tity span identification task by training it withWikipedia anchors, which can be deemed asgeneral-typed entities. Then we leverage thegazetteer-based distant supervision strategy totrain the model extract coarse-grained typedentities. Finally, we devise a self-supervisedauxiliary task to mine the fine-grained namedentity knowledge via clustering.Empiricalstudies on three public NER datasets demon-strate that our framework achieves significantimprovements against several pre-trained base-lines, establishing the new state-of-the-art per-formance on three benchmarks. Besides, weshow that our framework gains promising re-sults without using human-labeled trainingdata, demonstrating its effectiveness in label-few and low-resource scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mengge-etal-2020-coarse">
<titleInfo>
<title>Coarse-to-Fine Pre-training for Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xue</namePart>
<namePart type="family">Mengge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowen</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tingwen</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>More recently, Named Entity Recognition hasachieved great advances aided by pre-trainingapproaches such as BERT. However, currentpre-training techniques focus on building lan-guage modeling objectives to learn a gen-eral representation, ignoring the named entity-related knowledge. To this end, we proposea NER-specific pre-training framework to in-ject coarse-to-fine automatically mined entityknowledge into pre-trained models. Specifi-cally, we first warm-up the model via an en-tity span identification task by training it withWikipedia anchors, which can be deemed asgeneral-typed entities. Then we leverage thegazetteer-based distant supervision strategy totrain the model extract coarse-grained typedentities. Finally, we devise a self-supervisedauxiliary task to mine the fine-grained namedentity knowledge via clustering.Empiricalstudies on three public NER datasets demon-strate that our framework achieves significantimprovements against several pre-trained base-lines, establishing the new state-of-the-art per-formance on three benchmarks. Besides, weshow that our framework gains promising re-sults without using human-labeled trainingdata, demonstrating its effectiveness in label-few and low-resource scenarios.</abstract>
<identifier type="citekey">mengge-etal-2020-coarse</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.514</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.514</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>6345</start>
<end>6354</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Coarse-to-Fine Pre-training for Named Entity Recognition
%A Mengge, Xue
%A Yu, Bowen
%A Zhang, Zhenyu
%A Liu, Tingwen
%A Zhang, Yue
%A Wang, Bin
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F mengge-etal-2020-coarse
%X More recently, Named Entity Recognition hasachieved great advances aided by pre-trainingapproaches such as BERT. However, currentpre-training techniques focus on building lan-guage modeling objectives to learn a gen-eral representation, ignoring the named entity-related knowledge. To this end, we proposea NER-specific pre-training framework to in-ject coarse-to-fine automatically mined entityknowledge into pre-trained models. Specifi-cally, we first warm-up the model via an en-tity span identification task by training it withWikipedia anchors, which can be deemed asgeneral-typed entities. Then we leverage thegazetteer-based distant supervision strategy totrain the model extract coarse-grained typedentities. Finally, we devise a self-supervisedauxiliary task to mine the fine-grained namedentity knowledge via clustering.Empiricalstudies on three public NER datasets demon-strate that our framework achieves significantimprovements against several pre-trained base-lines, establishing the new state-of-the-art per-formance on three benchmarks. Besides, weshow that our framework gains promising re-sults without using human-labeled trainingdata, demonstrating its effectiveness in label-few and low-resource scenarios.
%R 10.18653/v1/2020.emnlp-main.514
%U https://aclanthology.org/2020.emnlp-main.514
%U https://doi.org/10.18653/v1/2020.emnlp-main.514
%P 6345-6354
Markdown (Informal)
[Coarse-to-Fine Pre-training for Named Entity Recognition](https://aclanthology.org/2020.emnlp-main.514) (Mengge et al., EMNLP 2020)
ACL
- Xue Mengge, Bowen Yu, Zhenyu Zhang, Tingwen Liu, Yue Zhang, and Bin Wang. 2020. Coarse-to-Fine Pre-training for Named Entity Recognition. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6345–6354, Online. Association for Computational Linguistics.