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

[31] Pre-trained language models with domain knowledge for biomedical extractive summarization
Xie Q.
Bishop J.A.
Tiwari P.
Ananiadou S.
Knowledge-Based Systems, 2022, 252
[32] Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewriting
Sun, Qingfeng
Xu, Can
Hu, Huang
Wang, Yujing
Miao, Jian
Geng, Xiubo
Chen, Yining
Xu, Fei
Jiang, Daxin
NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, 2022, : 3304 - 3318
[33] Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters
Xu, Yan
Ishii, Etsuko
Cahyawijaya, Samuel
Liu, Zihan
Winata, Genta Indra
Madotto, Andrea
Su, Dan
Fung, Pascale
PROCEEDINGS OF THE SECOND DIALDOC WORKSHOP ON DOCUMENT-GROUNDED DIALOGUE AND CONVERSATIONAL QUESTION ANSWERING (DIALDOC 2022), 2022, : 93 - 107
[34] PICKD: In-Situ Prompt Tuning for Knowledge-Grounded Dialogue Generation
Sarkar, Rajdeep
Goswami, Koustava
Arcan, Mihael
McCrae, John
ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2023, PT IV, 2023, 13938 : 124 - 136
[35] Plug-and-Play Knowledge Injection for Pre-trained Language Models
Zhang, Zhengyan
Zeng, Zhiyuan
Lin, Yankai
Wang, Huadong
Ye, Deming
Xiao, Chaojun
Han, Xu
Liu, Zhiyuan
Li, Peng
Sun, Maosong
Zhou, Jie
PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2023): LONG PAPERS, VOL 1, 2023, : 10641 - 10656
[36] Enhancing pre-trained language models with Chinese character morphological knowledge
Zheng, Zhenzhong
Wu, Xiaoming
Liu, Xiangzhi
INFORMATION PROCESSING & MANAGEMENT, 2025, 62 (01)
[37] Gauging, enriching and applying geography knowledge in Pre-trained Language Models
Ramrakhiyani, Nitin
Varma, Vasudeva
Palshikar, Girish Keshav
Pawar, Sachin
INFORMATION PROCESSING & MANAGEMENT, 2025, 62 (01)
[38] Pre-Trained Language-Meaning Models for Multilingual Parsing and Generation
Wang, Chunliu
Lai, Huiyuan
Nissim, Malvina
Bos, Johan
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL 2023, 2023, : 5586 - 5600
[39] Pre-trained Language Model Representations for Language Generation
Edunov, Sergey
Baevski, Alexei
Auli, Michael
2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, 2019, : 4052 - 4059
[40] CoLV: A Collaborative Latent Variable Model for Knowledge-Grounded Dialogue Generation
Zhan, Haolan
Shen, Lei
Chen, Hongshen
Zhang, Hainan
2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 2250 - 2261

← 1 2 3 4 5 →