@inproceedings{jia-etal-2020-entity,
title = "Entity Enhanced {BERT} Pre-training for {C}hinese {NER}",
author = "Jia, Chen and
Shi, Yuefeng and
Yang, Qinrong and
Zhang, Yue",
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.518",
doi = "10.18653/v1/2020.emnlp-main.518",
pages = "6384--6396",
abstract = "Character-level BERT pre-trained in Chinese suffers a limitation of lacking lexicon information, which shows effectiveness for Chinese NER. To integrate the lexicon into pre-trained LMs for Chinese NER, we investigate a semi-supervised entity enhanced BERT pre-training method. In particular, we first extract an entity lexicon from the relevant raw text using a new-word discovery method. We then integrate the entity information into BERT using Char-Entity-Transformer, which augments the self-attention using a combination of character and entity representations. In addition, an entity classification task helps inject the entity information into model parameters in pre-training. The pre-trained models are used for NER fine-tuning. Experiments on a news dataset and two datasets annotated by ourselves for NER in long-text show that our method is highly effective and achieves the best results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jia-etal-2020-entity">
<titleInfo>
<title>Entity Enhanced BERT Pre-training for Chinese NER</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuefeng</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qinrong</namePart>
<namePart type="family">Yang</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>
<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>Character-level BERT pre-trained in Chinese suffers a limitation of lacking lexicon information, which shows effectiveness for Chinese NER. To integrate the lexicon into pre-trained LMs for Chinese NER, we investigate a semi-supervised entity enhanced BERT pre-training method. In particular, we first extract an entity lexicon from the relevant raw text using a new-word discovery method. We then integrate the entity information into BERT using Char-Entity-Transformer, which augments the self-attention using a combination of character and entity representations. In addition, an entity classification task helps inject the entity information into model parameters in pre-training. The pre-trained models are used for NER fine-tuning. Experiments on a news dataset and two datasets annotated by ourselves for NER in long-text show that our method is highly effective and achieves the best results.</abstract>
<identifier type="citekey">jia-etal-2020-entity</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.518</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.518</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>6384</start>
<end>6396</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Entity Enhanced BERT Pre-training for Chinese NER
%A Jia, Chen
%A Shi, Yuefeng
%A Yang, Qinrong
%A Zhang, Yue
%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 jia-etal-2020-entity
%X Character-level BERT pre-trained in Chinese suffers a limitation of lacking lexicon information, which shows effectiveness for Chinese NER. To integrate the lexicon into pre-trained LMs for Chinese NER, we investigate a semi-supervised entity enhanced BERT pre-training method. In particular, we first extract an entity lexicon from the relevant raw text using a new-word discovery method. We then integrate the entity information into BERT using Char-Entity-Transformer, which augments the self-attention using a combination of character and entity representations. In addition, an entity classification task helps inject the entity information into model parameters in pre-training. The pre-trained models are used for NER fine-tuning. Experiments on a news dataset and two datasets annotated by ourselves for NER in long-text show that our method is highly effective and achieves the best results.
%R 10.18653/v1/2020.emnlp-main.518
%U https://aclanthology.org/2020.emnlp-main.518
%U https://doi.org/10.18653/v1/2020.emnlp-main.518
%P 6384-6396
Markdown (Informal)
[Entity Enhanced BERT Pre-training for Chinese NER](https://aclanthology.org/2020.emnlp-main.518) (Jia et al., EMNLP 2020)
ACL
- Chen Jia, Yuefeng Shi, Qinrong Yang, and Yue Zhang. 2020. Entity Enhanced BERT Pre-training for Chinese NER. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6384–6396, Online. Association for Computational Linguistics.