@inproceedings{lin-etal-2020-rigorous,
title = "A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?",
author = "Lin, Hongyu and
Lu, Yaojie and
Tang, Jialong and
Han, Xianpei and
Sun, Le and
Wei, Zhicheng and
Yuan, Nicholas Jing",
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.592",
doi = "10.18653/v1/2020.emnlp-main.592",
pages = "7291--7300",
abstract = "Fine-tuning pretrained model has achieved promising performance on standard NER benchmarks. Generally, these benchmarks are blessed with strong name regularity, high mention coverage and sufficient context diversity. Unfortunately, when scaling NER to open situations, these advantages may no longer exist. And therefore it raises a critical question of whether previous creditable approaches can still work well when facing these challenges. As there is no currently available dataset to investigate this problem, this paper proposes to conduct randomization test on standard benchmarks. Specifically, we erase name regularity, mention coverage and context diversity respectively from the benchmarks, in order to explore their impact on the generalization ability of models. To further verify our conclusions, we also construct a new open NER dataset that focuses on entity types with weaker name regularity and lower mention coverage to verify our conclusion. From both randomization test and empirical experiments, we draw the conclusions that 1) name regularity is critical for the models to generalize to unseen mentions; 2) high mention coverage may undermine the model generalization ability and 3) context patterns may not require enormous data to capture when using pretrained encoders.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2020-rigorous">
<titleInfo>
<title>A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?</title>
</titleInfo>
<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">Yaojie</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jialong</namePart>
<namePart type="family">Tang</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>
<name type="personal">
<namePart type="given">Zhicheng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="given">Jing</namePart>
<namePart type="family">Yuan</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>Fine-tuning pretrained model has achieved promising performance on standard NER benchmarks. Generally, these benchmarks are blessed with strong name regularity, high mention coverage and sufficient context diversity. Unfortunately, when scaling NER to open situations, these advantages may no longer exist. And therefore it raises a critical question of whether previous creditable approaches can still work well when facing these challenges. As there is no currently available dataset to investigate this problem, this paper proposes to conduct randomization test on standard benchmarks. Specifically, we erase name regularity, mention coverage and context diversity respectively from the benchmarks, in order to explore their impact on the generalization ability of models. To further verify our conclusions, we also construct a new open NER dataset that focuses on entity types with weaker name regularity and lower mention coverage to verify our conclusion. From both randomization test and empirical experiments, we draw the conclusions that 1) name regularity is critical for the models to generalize to unseen mentions; 2) high mention coverage may undermine the model generalization ability and 3) context patterns may not require enormous data to capture when using pretrained encoders.</abstract>
<identifier type="citekey">lin-etal-2020-rigorous</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.592</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.592</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>7291</start>
<end>7300</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?
%A Lin, Hongyu
%A Lu, Yaojie
%A Tang, Jialong
%A Han, Xianpei
%A Sun, Le
%A Wei, Zhicheng
%A Yuan, Nicholas Jing
%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 lin-etal-2020-rigorous
%X Fine-tuning pretrained model has achieved promising performance on standard NER benchmarks. Generally, these benchmarks are blessed with strong name regularity, high mention coverage and sufficient context diversity. Unfortunately, when scaling NER to open situations, these advantages may no longer exist. And therefore it raises a critical question of whether previous creditable approaches can still work well when facing these challenges. As there is no currently available dataset to investigate this problem, this paper proposes to conduct randomization test on standard benchmarks. Specifically, we erase name regularity, mention coverage and context diversity respectively from the benchmarks, in order to explore their impact on the generalization ability of models. To further verify our conclusions, we also construct a new open NER dataset that focuses on entity types with weaker name regularity and lower mention coverage to verify our conclusion. From both randomization test and empirical experiments, we draw the conclusions that 1) name regularity is critical for the models to generalize to unseen mentions; 2) high mention coverage may undermine the model generalization ability and 3) context patterns may not require enormous data to capture when using pretrained encoders.
%R 10.18653/v1/2020.emnlp-main.592
%U https://aclanthology.org/2020.emnlp-main.592
%U https://doi.org/10.18653/v1/2020.emnlp-main.592
%P 7291-7300
Markdown (Informal)
[A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?](https://aclanthology.org/2020.emnlp-main.592) (Lin et al., EMNLP 2020)
ACL