@inproceedings{kim-etal-2021-revisiting,
title = "Revisiting Pretraining with Adapters",
author = "Kim, Seungwon and
Shum, Alex and
Susanj, Nathan and
Hilgart, Jonathan",
editor = "Rogers, Anna and
Calixto, Iacer and
Vuli{\'c}, Ivan and
Saphra, Naomi and
Kassner, Nora and
Camburu, Oana-Maria and
Bansal, Trapit and
Shwartz, Vered",
booktitle = "Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.repl4nlp-1.11",
doi = "10.18653/v1/2021.repl4nlp-1.11",
pages = "90--99",
abstract = "Pretrained language models have served as the backbone for many state-of-the-art NLP results. These models are large and expensive to train. Recent work suggests that continued pretraining on task-specific data is worth the effort as pretraining leads to improved performance on downstream tasks. We explore alternatives to full-scale task-specific pretraining of language models through the use of adapter modules, a parameter-efficient approach to transfer learning. We find that adapter-based pretraining is able to achieve comparable results to task-specific pretraining while using a fraction of the overall trainable parameters. We further explore direct use of adapters without pretraining and find that the direct fine-tuning performs mostly on par with pretrained adapter models, contradicting previously proposed benefits of continual pretraining in full pretraining fine-tuning strategies. Lastly, we perform an ablation study on task-adaptive pretraining to investigate how different hyperparameter settings can change the effectiveness of the pretraining.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2021-revisiting">
<titleInfo>
<title>Revisiting Pretraining with Adapters</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seungwon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Shum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Susanj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Hilgart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iacer</namePart>
<namePart type="family">Calixto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naomi</namePart>
<namePart type="family">Saphra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Kassner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana-Maria</namePart>
<namePart type="family">Camburu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trapit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</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>Pretrained language models have served as the backbone for many state-of-the-art NLP results. These models are large and expensive to train. Recent work suggests that continued pretraining on task-specific data is worth the effort as pretraining leads to improved performance on downstream tasks. We explore alternatives to full-scale task-specific pretraining of language models through the use of adapter modules, a parameter-efficient approach to transfer learning. We find that adapter-based pretraining is able to achieve comparable results to task-specific pretraining while using a fraction of the overall trainable parameters. We further explore direct use of adapters without pretraining and find that the direct fine-tuning performs mostly on par with pretrained adapter models, contradicting previously proposed benefits of continual pretraining in full pretraining fine-tuning strategies. Lastly, we perform an ablation study on task-adaptive pretraining to investigate how different hyperparameter settings can change the effectiveness of the pretraining.</abstract>
<identifier type="citekey">kim-etal-2021-revisiting</identifier>
<identifier type="doi">10.18653/v1/2021.repl4nlp-1.11</identifier>
<location>
<url>https://aclanthology.org/2021.repl4nlp-1.11</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>90</start>
<end>99</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Revisiting Pretraining with Adapters
%A Kim, Seungwon
%A Shum, Alex
%A Susanj, Nathan
%A Hilgart, Jonathan
%Y Rogers, Anna
%Y Calixto, Iacer
%Y Vulić, Ivan
%Y Saphra, Naomi
%Y Kassner, Nora
%Y Camburu, Oana-Maria
%Y Bansal, Trapit
%Y Shwartz, Vered
%S Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F kim-etal-2021-revisiting
%X Pretrained language models have served as the backbone for many state-of-the-art NLP results. These models are large and expensive to train. Recent work suggests that continued pretraining on task-specific data is worth the effort as pretraining leads to improved performance on downstream tasks. We explore alternatives to full-scale task-specific pretraining of language models through the use of adapter modules, a parameter-efficient approach to transfer learning. We find that adapter-based pretraining is able to achieve comparable results to task-specific pretraining while using a fraction of the overall trainable parameters. We further explore direct use of adapters without pretraining and find that the direct fine-tuning performs mostly on par with pretrained adapter models, contradicting previously proposed benefits of continual pretraining in full pretraining fine-tuning strategies. Lastly, we perform an ablation study on task-adaptive pretraining to investigate how different hyperparameter settings can change the effectiveness of the pretraining.
%R 10.18653/v1/2021.repl4nlp-1.11
%U https://aclanthology.org/2021.repl4nlp-1.11
%U https://doi.org/10.18653/v1/2021.repl4nlp-1.11
%P 90-99
Markdown (Informal)
[Revisiting Pretraining with Adapters](https://aclanthology.org/2021.repl4nlp-1.11) (Kim et al., RepL4NLP 2021)
ACL
- Seungwon Kim, Alex Shum, Nathan Susanj, and Jonathan Hilgart. 2021. Revisiting Pretraining with Adapters. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pages 90–99, Online. Association for Computational Linguistics.