Knowledge-Grounded Dialogue Generation with Pre-trained Language Models

被引：0

作者：

Zhao, Xueliang ^{[1
,2
]}

Wu, Wei ^{[3
]}

Xu, Can ^{[4
]}

Tao, Chongyang ^{[4
]}

Zhao, Dongyan ^{[1
,2
]}

Yan, Rui ^{[1
,2
,5
]}

机构：

[1] Peking Univ, Wangxuan Inst Comp Technol, Beijing, Peoples R China

[2] Peking Univ, Ctr Data Sci, AAIS, Beijing, Peoples R China

[3] Meituan, Beijing, Peoples R China

[4] Microsoft Corp, Beijing, Peoples R China

[5] Beijing Acad Artificial Intelligence BAAI, Beijing, Peoples R China

来源：

PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP) | 2020年

基金：

美国国家科学基金会;

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We study knowledge-grounded dialogue generation with pre-trained language models. To leverage the redundant external knowledge under capacity constraint, we propose equipping response generation defined by a pre-trained language model with a knowledge selection module, and an unsupervised approach to jointly optimizing knowledge selection and response generation with unlabeled dialogues. Empirical results on two benchmarks indicate that our model can significantly outperform state-of-the-art methods in both automatic evaluation and human judgment.

引用

页码：3377 / 3390

页数：14

共 50 条

[1] Knowledge Grounded Pre-Trained Model For Dialogue Response Generation
Wang, Yanmeng
Rong, Wenge
Zhang, Jianfei
Ouyang, Yuanxin
Xiong, Zhang
[J]. 2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
[2] XDAI: A Tuning-free Framework for Exploiting Pre-trained Language Models in Knowledge Grounded Dialogue Generation
Yu, Jifan
Zhang, Xiaohan
Xu, Yifan
Lei, Xuanyu
Guan, Xinyu
Zhang, Jing
Hou, Lei
Li, Juanzi
Tang, Jie
[J]. PROCEEDINGS OF THE 28TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2022, 2022, : 4422 - 4432
[3] Knowledge Base Grounded Pre-trained Language Models via Distillation
Sourty, Raphael
Moreno, Jose G.
Servant, Francois-Paul
Tamine, Lynda
[J]. 39TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, SAC 2024, 2024, : 1617 - 1625
[4] Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation
Li, Yu
Peng, Baolin
Shen, Yelong
Mao, Yi
Liden, Lars
Yu, Zhou
Gao, Jianfeng
[J]. NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, 2022, : 206 - 218
[5] An Investigation of Suitability of Pre-Trained Language Models for Dialogue Generation - Avoiding Discrepancies
Zeng, Yan
Nie, Jian-Yun
[J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 4481 - 4494
[6] Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey
Bhargava, Prajjwal
Ng, Vincent
[J]. THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 12317 - 12325
[7] Knowledge Inheritance for Pre-trained Language Models
Qin, Yujia
Lin, Yankai
Yi, Jing
Zhang, Jiajie
Han, Xu
Zhang, Zhengyan
Su, Yusheng
Liu, Zhiyuan
Li, Peng
Sun, Maosong
Zhou, Jie
[J]. NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, 2022, : 3921 - 3937
[8] Probing Pre-Trained Language Models for Disease Knowledge
Alghanmi, Israa
Espinosa-Anke, Luis
Schockaert, Steven
[J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 3023 - 3033
[9] Dynamic Knowledge Distillation for Pre-trained Language Models
Li, Lei
Lin, Yankai
Ren, Shuhuai
Li, Peng
Zhou, Jie
Sun, Xu
[J]. 2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 379 - 389
[10] Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue Generation
Zheng, Wen
Milic-Frayling, Natasa
Zhou, Ke
[J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, 2020,

← 1 2 3 4 5 →