@inproceedings{zhou-etal-2021-multi,
title = "Multi-Grained Knowledge Distillation for Named Entity Recognition",
author = "Zhou, Xuan and
Zhang, Xiao and
Tao, Chenyang and
Chen, Junya and
Xu, Bing and
Wang, Wei and
Xiao, Jing",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.454",
doi = "10.18653/v1/2021.naacl-main.454",
pages = "5704--5716",
abstract = "Although pre-trained big models (e.g., BERT, ERNIE, XLNet, GPT3 etc.) have delivered top performance in Seq2seq modeling, their deployments in real-world applications are often hindered by the excessive computations and memory demand involved. For many applications, including named entity recognition (NER), matching the state-of-the-art result under budget has attracted considerable attention. Drawing power from the recent advance in knowledge distillation (KD), this work presents a novel distillation scheme to efficiently transfer the knowledge learned from big models to their more affordable counterpart. Our solution highlights the construction of surrogate labels through the k-best Viterbi algorithm to distill knowledge from the teacher model. To maximally assimilate knowledge into the student model, we propose a multi-grained distillation scheme, which integrates cross entropy involved in conditional random field (CRF) and fuzzy learning. To validate the effectiveness of our proposal, we conducted a comprehensive evaluation on five NER benchmarks, reporting cross-the-board performance gains relative to competing prior-arts. We further discuss ablation results to dissect our gains.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2021-multi">
<titleInfo>
<title>Multi-Grained Knowledge Distillation for Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenyang</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junya</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>Although pre-trained big models (e.g., BERT, ERNIE, XLNet, GPT3 etc.) have delivered top performance in Seq2seq modeling, their deployments in real-world applications are often hindered by the excessive computations and memory demand involved. For many applications, including named entity recognition (NER), matching the state-of-the-art result under budget has attracted considerable attention. Drawing power from the recent advance in knowledge distillation (KD), this work presents a novel distillation scheme to efficiently transfer the knowledge learned from big models to their more affordable counterpart. Our solution highlights the construction of surrogate labels through the k-best Viterbi algorithm to distill knowledge from the teacher model. To maximally assimilate knowledge into the student model, we propose a multi-grained distillation scheme, which integrates cross entropy involved in conditional random field (CRF) and fuzzy learning. To validate the effectiveness of our proposal, we conducted a comprehensive evaluation on five NER benchmarks, reporting cross-the-board performance gains relative to competing prior-arts. We further discuss ablation results to dissect our gains.</abstract>
<identifier type="citekey">zhou-etal-2021-multi</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.454</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.454</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>5704</start>
<end>5716</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Grained Knowledge Distillation for Named Entity Recognition
%A Zhou, Xuan
%A Zhang, Xiao
%A Tao, Chenyang
%A Chen, Junya
%A Xu, Bing
%A Wang, Wei
%A Xiao, Jing
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F zhou-etal-2021-multi
%X Although pre-trained big models (e.g., BERT, ERNIE, XLNet, GPT3 etc.) have delivered top performance in Seq2seq modeling, their deployments in real-world applications are often hindered by the excessive computations and memory demand involved. For many applications, including named entity recognition (NER), matching the state-of-the-art result under budget has attracted considerable attention. Drawing power from the recent advance in knowledge distillation (KD), this work presents a novel distillation scheme to efficiently transfer the knowledge learned from big models to their more affordable counterpart. Our solution highlights the construction of surrogate labels through the k-best Viterbi algorithm to distill knowledge from the teacher model. To maximally assimilate knowledge into the student model, we propose a multi-grained distillation scheme, which integrates cross entropy involved in conditional random field (CRF) and fuzzy learning. To validate the effectiveness of our proposal, we conducted a comprehensive evaluation on five NER benchmarks, reporting cross-the-board performance gains relative to competing prior-arts. We further discuss ablation results to dissect our gains.
%R 10.18653/v1/2021.naacl-main.454
%U https://aclanthology.org/2021.naacl-main.454
%U https://doi.org/10.18653/v1/2021.naacl-main.454
%P 5704-5716
Markdown (Informal)
[Multi-Grained Knowledge Distillation for Named Entity Recognition](https://aclanthology.org/2021.naacl-main.454) (Zhou et al., NAACL 2021)
ACL
- Xuan Zhou, Xiao Zhang, Chenyang Tao, Junya Chen, Bing Xu, Wei Wang, and Jing Xiao. 2021. Multi-Grained Knowledge Distillation for Named Entity Recognition. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5704–5716, Online. Association for Computational Linguistics.