@inproceedings{peters-etal-2019-tune,
title = "To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks",
author = "Peters, Matthew E. and
Ruder, Sebastian and
Smith, Noah A.",
editor = "Augenstein, Isabelle and
Gella, Spandana and
Ruder, Sebastian and
Kann, Katharina and
Can, Burcu and
Welbl, Johannes and
Conneau, Alexis and
Ren, Xiang and
Rei, Marek",
booktitle = "Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4302",
doi = "10.18653/v1/W19-4302",
pages = "7--14",
abstract = "While most previous work has focused on different pretraining objectives and architectures for transfer learning, we ask how to best adapt the pretrained model to a given target task. We focus on the two most common forms of adaptation, feature extraction (where the pretrained weights are frozen), and directly fine-tuning the pretrained model. Our empirical results across diverse NLP tasks with two state-of-the-art models show that the relative performance of fine-tuning vs. feature extraction depends on the similarity of the pretraining and target tasks. We explore possible explanations for this finding and provide a set of adaptation guidelines for the NLP practitioner.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peters-etal-2019-tune">
<titleInfo>
<title>To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Peters</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burcu</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Welbl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Conneau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Rei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While most previous work has focused on different pretraining objectives and architectures for transfer learning, we ask how to best adapt the pretrained model to a given target task. We focus on the two most common forms of adaptation, feature extraction (where the pretrained weights are frozen), and directly fine-tuning the pretrained model. Our empirical results across diverse NLP tasks with two state-of-the-art models show that the relative performance of fine-tuning vs. feature extraction depends on the similarity of the pretraining and target tasks. We explore possible explanations for this finding and provide a set of adaptation guidelines for the NLP practitioner.</abstract>
<identifier type="citekey">peters-etal-2019-tune</identifier>
<identifier type="doi">10.18653/v1/W19-4302</identifier>
<location>
<url>https://aclanthology.org/W19-4302</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>7</start>
<end>14</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks
%A Peters, Matthew E.
%A Ruder, Sebastian
%A Smith, Noah A.
%Y Augenstein, Isabelle
%Y Gella, Spandana
%Y Ruder, Sebastian
%Y Kann, Katharina
%Y Can, Burcu
%Y Welbl, Johannes
%Y Conneau, Alexis
%Y Ren, Xiang
%Y Rei, Marek
%S Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F peters-etal-2019-tune
%X While most previous work has focused on different pretraining objectives and architectures for transfer learning, we ask how to best adapt the pretrained model to a given target task. We focus on the two most common forms of adaptation, feature extraction (where the pretrained weights are frozen), and directly fine-tuning the pretrained model. Our empirical results across diverse NLP tasks with two state-of-the-art models show that the relative performance of fine-tuning vs. feature extraction depends on the similarity of the pretraining and target tasks. We explore possible explanations for this finding and provide a set of adaptation guidelines for the NLP practitioner.
%R 10.18653/v1/W19-4302
%U https://aclanthology.org/W19-4302
%U https://doi.org/10.18653/v1/W19-4302
%P 7-14
Markdown (Informal)
[To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks](https://aclanthology.org/W19-4302) (Peters et al., RepL4NLP 2019)
ACL