@inproceedings{lin-etal-2020-exploring,
title = "Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning",
author = "Lin, Zhaojiang and
Madotto, Andrea and
Fung, Pascale",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.41",
doi = "10.18653/v1/2020.findings-emnlp.41",
pages = "441--459",
abstract = "Fine-tuning pre-trained generative language models to down-stream language generation tasks has shown promising results. However, this comes with the cost of having a single, large model for each task, which is not ideal in low-memory/power scenarios (e.g., mobile). In this paper, we propose an effective way to fine-tune multiple down-stream generation tasks simultaneously using a single, large pretrained model. The experiments on five diverse language generation tasks show that by just using an additional 2-3{\%} parameters for each task, our model can maintain or even improve the performance of fine-tuning the whole model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2020-exploring">
<titleInfo>
<title>Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhaojiang</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Madotto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</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>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<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 pre-trained generative language models to down-stream language generation tasks has shown promising results. However, this comes with the cost of having a single, large model for each task, which is not ideal in low-memory/power scenarios (e.g., mobile). In this paper, we propose an effective way to fine-tune multiple down-stream generation tasks simultaneously using a single, large pretrained model. The experiments on five diverse language generation tasks show that by just using an additional 2-3% parameters for each task, our model can maintain or even improve the performance of fine-tuning the whole model.</abstract>
<identifier type="citekey">lin-etal-2020-exploring</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.41</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.41</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>441</start>
<end>459</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning
%A Lin, Zhaojiang
%A Madotto, Andrea
%A Fung, Pascale
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F lin-etal-2020-exploring
%X Fine-tuning pre-trained generative language models to down-stream language generation tasks has shown promising results. However, this comes with the cost of having a single, large model for each task, which is not ideal in low-memory/power scenarios (e.g., mobile). In this paper, we propose an effective way to fine-tune multiple down-stream generation tasks simultaneously using a single, large pretrained model. The experiments on five diverse language generation tasks show that by just using an additional 2-3% parameters for each task, our model can maintain or even improve the performance of fine-tuning the whole model.
%R 10.18653/v1/2020.findings-emnlp.41
%U https://aclanthology.org/2020.findings-emnlp.41
%U https://doi.org/10.18653/v1/2020.findings-emnlp.41
%P 441-459
Markdown (Informal)
[Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning](https://aclanthology.org/2020.findings-emnlp.41) (Lin et al., Findings 2020)
ACL