ACL Findings2021
Knowledge-Grounded Dialogue Generation with Term-level De-noising
Abstract
Dialogue generation has been improved through injecting knowledge into generative models. However, addition of knowledge through simple selection of sentences or paragraphs is likely to introduce noise and diminish the effectiveness of the generative models. In this paper, we present a novel Knowledge Term Weighting Model (KTWM) that incorporates term-level de-noising of the selected knowledge. KTWM includes a module for generating Simulated Response Vectors (SRVs) and uses SRVs attention distributions with the knowledge embeddings to determine knowledge term weights. Our experiments demonstrate that KTWM, combined with various knowledge selection algorithms, consistently achieves statistically significant improvements over methods without term weighting when applied to two publicly available datasets Wizard of Wikipedia (Wiz) and Holl-E. The results are particularly improved for the Wiz test data with unseen topics, demonstrating the robustness of the KTWM noise-reduction approach.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue Generation cites Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
- Knowledge-Grounded Dialogue Generation with Pre-trained Language Models cites Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
- Knowledge-Grounded Dialogue Generation with Pre-trained Language Models cites Low-Resource Knowledge-Grounded Dialogue Generation
- There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning cites Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
- There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning cites Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
- Contextual Knowledge Learning for Dialogue Generation cites Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
- Contextual Knowledge Learning for Dialogue Generation cites Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue Generation
- Contextual Knowledge Learning for Dialogue Generation cites Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
- Contextual Knowledge Learning for Dialogue Generation cites Low-Resource Knowledge-Grounded Dialogue Generation
Cited by top-tier papers2
- Contextual Knowledge Learning for Dialogue GenerationWen Zheng, Natasa Milic-Frayling, Ke ZhouACL 2023 · 6 citations
- There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference LearningXueliang Zhao, Tingchen Fu, Chongyang Tao, Rui YanEMNLP 2022 · 2 citations
Builds on4
- Sequential Latent Knowledge Selection for Knowledge-Grounded DialogueByeongchang Kim, Jaewoo Ahn, Gunhee KimICLR 2020 · 179 citations
- Knowledge-Grounded Dialogue Generation with Pre-trained Language ModelsXueliang Zhao, Wei Wu, Can Xu, Chongyang Tao et al.EMNLP 2020 · 153 citations
- Low-Resource Knowledge-Grounded Dialogue GenerationXueliang Zhao, Wei Wu, Chongyang Tao, Can Xu et al.ICLR 2020 · 115 citations
- Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue GenerationWen Zheng, Natasa Milic-Frayling, Ke ZhouEMNLP Findings 2020 · 8 citations
Related papers
- CoLV: A Collaborative Latent Variable Model for Knowledge-Grounded Dialogue GenerationHaolan Zhan, Lei Shen, Hongshen Chen, Hainan ZhangEMNLP 2021 · 15 citations
- Topic-Aware Response Generation in Task-Oriented Dialogue with Unstructured Knowledge AccessYue Feng, Gerasimos Lampouras, Ignacio IacobacciEMNLP Findings 2022 · 6 citations
- Improving Knowledge-Aware Dialogue Generation via Knowledge Base Question AnsweringJian Wang, Junhao Liu, Wei Bi, Xiaojiang Liu et al.AAAI 2020 · 52 citations
- Improving Knowledge-Aware Dialogue Response Generation by Using Human-Written Prototype DialoguesSixing Wu, Ying Li, Dawei Zhang, Zhonghai WuEMNLP Findings 2020 · 17 citations
- Towards Faithful Dialogues via Focus LearningYifan Deng, Xingsheng Zhang, Heyan Huang, Yue HuACL 2023 · 4 citations
