Graph vs. Sequence: An Empirical Study on Knowledge Forms for Knowledge-Grounded Dialogue
Yizhe Yang, Heyan Huang, Yuhang Liu, Yang Gao
摘要
Knowledge-grounded dialogue is a task of gener- ating an informative response based on both the dialogue history and external knowledge source. In general, there are two forms of knowledge: manu- ally annotated knowledge graphs and knowledge text from website. From various evaluation viewpoints, each type of knowledge has advantages and downsides. To further distinguish the principles and determinants from the intricate factors, we conduct a thorough experiment and study on the task to answer three essential questions. The ques- tions involve the choice of appropriate knowledge form, the degree of mutual effects between knowl- edge and the model selection, and the few-shot performance of knowledge. Supported by statistical shreds of evidence, we offer conclusive solutions and sensible suggestions for directions and standards of future research.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper10
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida 等NeurIPS 2022 · 被引用 24,707 次
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad 等ACL 2020 · 被引用 1,224 次
- Knowledge-Grounded Dialogue Generation with Pre-trained Language ModelsXueliang Zhao, Wei Wu, Can Xu, Chongyang Tao 等EMNLP 2020 · 被引用 153 次
- KGPT: Knowledge-Grounded Pre-Training for Data-to-Text GenerationWenhu Chen, Yu Su, Xifeng Yan, William Yang WangEMNLP 2020 · 被引用 115 次
- Low-Resource Knowledge-Grounded Dialogue GenerationXueliang Zhao, Wei Wu, Chongyang Tao, Can Xu 等ICLR 2020 · 被引用 115 次
相关 Paper
- KPT: Keyword-Guided Pre-training for Grounded Dialog GenerationQi Zhu, Fei Mi, Zheng Zhang, Yasheng Wang 等AAAI 2023 · 被引用 5 次
- CoLV: A Collaborative Latent Variable Model for Knowledge-Grounded Dialogue GenerationHaolan Zhan, Lei Shen, Hongshen Chen, Hainan ZhangEMNLP 2021 · 被引用 15 次
- Sequential Latent Knowledge Selection for Knowledge-Grounded DialogueByeongchang Kim, Jaewoo Ahn, Gunhee KimICLR 2020 · 被引用 179 次
- Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded DialogueLang Qin, Yao Zhang, Hongru Liang, Jun Wang 等EMNLP 2023 · 被引用 1 次
- Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive LearningJiaan Wang, Jianfeng Qu, Kexin Wang, Zhixu Li 等AAAI 2024 · 被引用 5 次
