@inproceedings{yang-etal-2024-pek,
title = "{PEK}: A Parameter-Efficient Framework for Knowledge-Grounded Dialogue Generation",
author = "Yang, Pan and
Song, Dandan and
Wu, Zhijing and
Zhou, Yanru",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.550",
pages = "9261--9273",
abstract = "Pre-trained language models (PLMs) have shown great dialogue generation capability in different scenarios. However, the huge VRAM consumption when fine-tuning them is one of their drawbacks. PEFT approaches can significantly reduce the number of trainable parameters, which enables us to fine-tune larger dialogue generation models. However, the reduction in parameter quantity can diminish a PLM{'}s expressive capacity and affect the PLM{'}s learning from certain specific examples like knowledge-related conversations. Previous works have demonstrated that injecting external knowledge into dialogue generation models can improve the model{'}s performance in knowledge-related conversations. Nonetheless, these methods are designed for the scenario where most parameters of the entire framework are trainable. In this paper, we propose PEK, a parameter-efficient framework for knowledge-enhanced dialogue generation. It enables PLMs to leverage external knowledge documents and knowledge graphs to enhance its generation capabilities with an acceptable number of trainable parameters. Evaluation results on the Wizard of Wikipedia and CMU{\_}DoG datasets show that our approach outperforms baseline methods on multiple evaluation metrics, which validates the effectiveness of our approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2024-pek">
<titleInfo>
<title>PEK: A Parameter-Efficient Framework for Knowledge-Grounded Dialogue Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pan</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dandan</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhijing</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanru</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained language models (PLMs) have shown great dialogue generation capability in different scenarios. However, the huge VRAM consumption when fine-tuning them is one of their drawbacks. PEFT approaches can significantly reduce the number of trainable parameters, which enables us to fine-tune larger dialogue generation models. However, the reduction in parameter quantity can diminish a PLM’s expressive capacity and affect the PLM’s learning from certain specific examples like knowledge-related conversations. Previous works have demonstrated that injecting external knowledge into dialogue generation models can improve the model’s performance in knowledge-related conversations. Nonetheless, these methods are designed for the scenario where most parameters of the entire framework are trainable. In this paper, we propose PEK, a parameter-efficient framework for knowledge-enhanced dialogue generation. It enables PLMs to leverage external knowledge documents and knowledge graphs to enhance its generation capabilities with an acceptable number of trainable parameters. Evaluation results on the Wizard of Wikipedia and CMU_DoG datasets show that our approach outperforms baseline methods on multiple evaluation metrics, which validates the effectiveness of our approach.</abstract>
<identifier type="citekey">yang-etal-2024-pek</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.550</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>9261</start>
<end>9273</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PEK: A Parameter-Efficient Framework for Knowledge-Grounded Dialogue Generation
%A Yang, Pan
%A Song, Dandan
%A Wu, Zhijing
%A Zhou, Yanru
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F yang-etal-2024-pek
%X Pre-trained language models (PLMs) have shown great dialogue generation capability in different scenarios. However, the huge VRAM consumption when fine-tuning them is one of their drawbacks. PEFT approaches can significantly reduce the number of trainable parameters, which enables us to fine-tune larger dialogue generation models. However, the reduction in parameter quantity can diminish a PLM’s expressive capacity and affect the PLM’s learning from certain specific examples like knowledge-related conversations. Previous works have demonstrated that injecting external knowledge into dialogue generation models can improve the model’s performance in knowledge-related conversations. Nonetheless, these methods are designed for the scenario where most parameters of the entire framework are trainable. In this paper, we propose PEK, a parameter-efficient framework for knowledge-enhanced dialogue generation. It enables PLMs to leverage external knowledge documents and knowledge graphs to enhance its generation capabilities with an acceptable number of trainable parameters. Evaluation results on the Wizard of Wikipedia and CMU_DoG datasets show that our approach outperforms baseline methods on multiple evaluation metrics, which validates the effectiveness of our approach.
%U https://aclanthology.org/2024.findings-acl.550
%P 9261-9273
Markdown (Informal)
[PEK: A Parameter-Efficient Framework for Knowledge-Grounded Dialogue Generation](https://aclanthology.org/2024.findings-acl.550) (Yang et al., Findings 2024)
ACL