@inproceedings{zhao-etal-2023-spc,
title = "{SPC}: Soft Prompt Construction for Cross Domain Generalization",
author = "Zhao, Wenbo and
Gupta, Arpit and
Chung, Tagyoung and
Huang, Jing",
editor = "Can, Burcu and
Mozes, Maximilian and
Cahyawijaya, Samuel and
Saphra, Naomi and
Kassner, Nora and
Ravfogel, Shauli and
Ravichander, Abhilasha and
Zhao, Chen and
Augenstein, Isabelle and
Rogers, Anna and
Cho, Kyunghyun and
Grefenstette, Edward and
Voita, Lena",
booktitle = "Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.repl4nlp-1.10",
doi = "10.18653/v1/2023.repl4nlp-1.10",
pages = "118--130",
abstract = "Recent advances in prompt tuning have proven effective as a new language modeling paradigm for various natural language understanding tasks. However, it is challenging to adapt the soft prompt embeddings to different domains or generalize to low-data settings when learning soft prompts itself is unstable, task-specific, and bias-prone. This paper proposes a principled learning framework{---}soft prompt construction (SPC){---}to facilitate learning domain-adaptable soft prompts. Derived from the SPC framework is a simple loss that can plug into various models and tuning approaches to improve their cross-domain performance. We show SPC can improve upon SOTA for contextual query rewriting, summarization, and paraphrase detection by up to 5{\%}, 19{\%}, and 16{\%}, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2023-spc">
<titleInfo>
<title>SPC: Soft Prompt Construction for Cross Domain Generalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenbo</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arpit</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tagyoung</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)</title>
</titleInfo>
<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">Maximilian</namePart>
<namePart type="family">Mozes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Cahyawijaya</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">Shauli</namePart>
<namePart type="family">Ravfogel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhilasha</namePart>
<namePart type="family">Ravichander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Grefenstette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lena</namePart>
<namePart type="family">Voita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in prompt tuning have proven effective as a new language modeling paradigm for various natural language understanding tasks. However, it is challenging to adapt the soft prompt embeddings to different domains or generalize to low-data settings when learning soft prompts itself is unstable, task-specific, and bias-prone. This paper proposes a principled learning framework—soft prompt construction (SPC)—to facilitate learning domain-adaptable soft prompts. Derived from the SPC framework is a simple loss that can plug into various models and tuning approaches to improve their cross-domain performance. We show SPC can improve upon SOTA for contextual query rewriting, summarization, and paraphrase detection by up to 5%, 19%, and 16%, respectively.</abstract>
<identifier type="citekey">zhao-etal-2023-spc</identifier>
<identifier type="doi">10.18653/v1/2023.repl4nlp-1.10</identifier>
<location>
<url>https://aclanthology.org/2023.repl4nlp-1.10</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>118</start>
<end>130</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SPC: Soft Prompt Construction for Cross Domain Generalization
%A Zhao, Wenbo
%A Gupta, Arpit
%A Chung, Tagyoung
%A Huang, Jing
%Y Can, Burcu
%Y Mozes, Maximilian
%Y Cahyawijaya, Samuel
%Y Saphra, Naomi
%Y Kassner, Nora
%Y Ravfogel, Shauli
%Y Ravichander, Abhilasha
%Y Zhao, Chen
%Y Augenstein, Isabelle
%Y Rogers, Anna
%Y Cho, Kyunghyun
%Y Grefenstette, Edward
%Y Voita, Lena
%S Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zhao-etal-2023-spc
%X Recent advances in prompt tuning have proven effective as a new language modeling paradigm for various natural language understanding tasks. However, it is challenging to adapt the soft prompt embeddings to different domains or generalize to low-data settings when learning soft prompts itself is unstable, task-specific, and bias-prone. This paper proposes a principled learning framework—soft prompt construction (SPC)—to facilitate learning domain-adaptable soft prompts. Derived from the SPC framework is a simple loss that can plug into various models and tuning approaches to improve their cross-domain performance. We show SPC can improve upon SOTA for contextual query rewriting, summarization, and paraphrase detection by up to 5%, 19%, and 16%, respectively.
%R 10.18653/v1/2023.repl4nlp-1.10
%U https://aclanthology.org/2023.repl4nlp-1.10
%U https://doi.org/10.18653/v1/2023.repl4nlp-1.10
%P 118-130
Markdown (Informal)
[SPC: Soft Prompt Construction for Cross Domain Generalization](https://aclanthology.org/2023.repl4nlp-1.10) (Zhao et al., RepL4NLP 2023)
ACL