@inproceedings{wu-etal-2023-parameter,
title = "Parameter Efficient Multi-task Fine-tuning by Learning to Transfer Token-wise Prompts",
author = "Wu, Muling and
Liu, Wenhao and
Xu, Jianhan and
Lv, Changze and
Ling, Zixuan and
Li, Tianlong and
Huang, Longtao and
Zheng, Xiaoqing and
Huang, Xuanjing",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.584",
doi = "10.18653/v1/2023.findings-emnlp.584",
pages = "8734--8746",
abstract = "Prompt tuning has been proven to be successful on various tasks by incorporating a small number of trainable parameters while freezing large pre-trained language models (PLMs). However, it is still unsettled how to generate more proper prompts for any individual examples and how to extend prompt tuning to multi-task learning scenarios by leveraging cross-task features. To address these challenges, we propose a token-wise prompt tuning (TPT), in which a bank of finer-grained soft prompt tokens is built for multi-task learning by memory network. The tokens are retrieved from the bank against an input example and assembled to an instance-dependent prompt. Extensive experimental results on 14 datasets demonstrated that the models enhanced by our TPT performed far better than full parameter fine-tuned models and achieved state-of-the-art by tuning only 0.035{\%} parameters.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2023-parameter">
<titleInfo>
<title>Parameter Efficient Multi-task Fine-tuning by Learning to Transfer Token-wise Prompts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muling</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianhan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changze</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zixuan</namePart>
<namePart type="family">Ling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianlong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longtao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqing</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Prompt tuning has been proven to be successful on various tasks by incorporating a small number of trainable parameters while freezing large pre-trained language models (PLMs). However, it is still unsettled how to generate more proper prompts for any individual examples and how to extend prompt tuning to multi-task learning scenarios by leveraging cross-task features. To address these challenges, we propose a token-wise prompt tuning (TPT), in which a bank of finer-grained soft prompt tokens is built for multi-task learning by memory network. The tokens are retrieved from the bank against an input example and assembled to an instance-dependent prompt. Extensive experimental results on 14 datasets demonstrated that the models enhanced by our TPT performed far better than full parameter fine-tuned models and achieved state-of-the-art by tuning only 0.035% parameters.</abstract>
<identifier type="citekey">wu-etal-2023-parameter</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.584</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.584</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>8734</start>
<end>8746</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parameter Efficient Multi-task Fine-tuning by Learning to Transfer Token-wise Prompts
%A Wu, Muling
%A Liu, Wenhao
%A Xu, Jianhan
%A Lv, Changze
%A Ling, Zixuan
%A Li, Tianlong
%A Huang, Longtao
%A Zheng, Xiaoqing
%A Huang, Xuanjing
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F wu-etal-2023-parameter
%X Prompt tuning has been proven to be successful on various tasks by incorporating a small number of trainable parameters while freezing large pre-trained language models (PLMs). However, it is still unsettled how to generate more proper prompts for any individual examples and how to extend prompt tuning to multi-task learning scenarios by leveraging cross-task features. To address these challenges, we propose a token-wise prompt tuning (TPT), in which a bank of finer-grained soft prompt tokens is built for multi-task learning by memory network. The tokens are retrieved from the bank against an input example and assembled to an instance-dependent prompt. Extensive experimental results on 14 datasets demonstrated that the models enhanced by our TPT performed far better than full parameter fine-tuned models and achieved state-of-the-art by tuning only 0.035% parameters.
%R 10.18653/v1/2023.findings-emnlp.584
%U https://aclanthology.org/2023.findings-emnlp.584
%U https://doi.org/10.18653/v1/2023.findings-emnlp.584
%P 8734-8746
Markdown (Informal)
[Parameter Efficient Multi-task Fine-tuning by Learning to Transfer Token-wise Prompts](https://aclanthology.org/2023.findings-emnlp.584) (Wu et al., Findings 2023)
ACL
- Muling Wu, Wenhao Liu, Jianhan Xu, Changze Lv, Zixuan Ling, Tianlong Li, Longtao Huang, Xiaoqing Zheng, and Xuanjing Huang. 2023. Parameter Efficient Multi-task Fine-tuning by Learning to Transfer Token-wise Prompts. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8734–8746, Singapore. Association for Computational Linguistics.