@inproceedings{shen-etal-2022-palt,
title = "{PALT}: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion",
author = "Shen, Jianhao and
Wang, Chenguang and
Yuan, Ye and
Han, Jiawei and
Ji, Heng and
Sen, Koushik and
Zhang, Ming and
Song, Dawn",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.281",
doi = "10.18653/v1/2022.findings-emnlp.281",
pages = "3833--3847",
abstract = "This paper presents a parameter-lite transfer learning approach of pretrained language models (LM) for knowledge graph (KG) completion. Instead of finetuning, which modifies all LM parameters, we only tune a few new parameters while keeping the original LM parameters fixed. We establish this via reformulating KG completion as a {``}fill-in-the-blank{''} task, and introducing a parameter-lite encoder on top of the original LMs. We show that, by tuning far fewer parameters than finetuning, LMs transfer non-trivially to most tasks and reach competitiveness with prior state-of-the-art approaches. For instance, we outperform the fully finetuning approaches on a KG completion benchmark by tuning only 1{\%} of the parameters.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-etal-2022-palt">
<titleInfo>
<title>PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianhao</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenguang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ye</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koushik</namePart>
<namePart type="family">Sen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawn</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a parameter-lite transfer learning approach of pretrained language models (LM) for knowledge graph (KG) completion. Instead of finetuning, which modifies all LM parameters, we only tune a few new parameters while keeping the original LM parameters fixed. We establish this via reformulating KG completion as a “fill-in-the-blank” task, and introducing a parameter-lite encoder on top of the original LMs. We show that, by tuning far fewer parameters than finetuning, LMs transfer non-trivially to most tasks and reach competitiveness with prior state-of-the-art approaches. For instance, we outperform the fully finetuning approaches on a KG completion benchmark by tuning only 1% of the parameters.</abstract>
<identifier type="citekey">shen-etal-2022-palt</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.281</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.281</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>3833</start>
<end>3847</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion
%A Shen, Jianhao
%A Wang, Chenguang
%A Yuan, Ye
%A Han, Jiawei
%A Ji, Heng
%A Sen, Koushik
%A Zhang, Ming
%A Song, Dawn
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F shen-etal-2022-palt
%X This paper presents a parameter-lite transfer learning approach of pretrained language models (LM) for knowledge graph (KG) completion. Instead of finetuning, which modifies all LM parameters, we only tune a few new parameters while keeping the original LM parameters fixed. We establish this via reformulating KG completion as a “fill-in-the-blank” task, and introducing a parameter-lite encoder on top of the original LMs. We show that, by tuning far fewer parameters than finetuning, LMs transfer non-trivially to most tasks and reach competitiveness with prior state-of-the-art approaches. For instance, we outperform the fully finetuning approaches on a KG completion benchmark by tuning only 1% of the parameters.
%R 10.18653/v1/2022.findings-emnlp.281
%U https://aclanthology.org/2022.findings-emnlp.281
%U https://doi.org/10.18653/v1/2022.findings-emnlp.281
%P 3833-3847
Markdown (Informal)
[PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion](https://aclanthology.org/2022.findings-emnlp.281) (Shen et al., Findings 2022)
ACL
- Jianhao Shen, Chenguang Wang, Ye Yuan, Jiawei Han, Heng Ji, Koushik Sen, Ming Zhang, and Dawn Song. 2022. PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3833–3847, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.