Lune

ACL Findings2022

KSAM: Infusing Multi-Source Knowledge into Dialogue Generation via Knowledge Source Aware Multi-Head Decoding

Sixing Wu, Ying Li, Dawei Zhang, Zhonghai Wu

Abstract

Knowledge-enhanced methods have bridged the gap between human beings and machines in generating dialogue responses. However, most previous works solely seek knowledge from a single source, and thus they often fail to obtain available knowledge because of the insufficient coverage of a single knowledge source. To this end, infusing knowledge from multiple sources becomes a trend. This paper proposes a novel approach Knowledge Source Aware Multi-Head Decoding, KSAM, to infuse multi-source knowledge into dialogue generation more efficiently. Rather than following the traditional single decoder paradigm, KSAM uses multiple independent source-aware decoder heads to alleviate three challenging problems in infusing multi-source knowledge, namely, the diversity among different knowledge sources, the indefinite knowledge alignment issue, and the insufficient flexibility/scalability in knowledge usage. Experiments on a Chinese multi-source knowledge-aligned dataset demonstrate the superior performance of KSAM against various competitive approaches.

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.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop PathsXiangqing Shen, Siwei Wu, Rui XiaACL 2023 · 3 citations
  2. M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple PartitionsZheng Wang, Shu Xian Teo, Jieer Ouyang, Yongjun Xu et al.ACL 2024

Builds on13

  1. Sequential Latent Knowledge Selection for Knowledge-Grounded DialogueByeongchang Kim, Jaewoo Ahn, Gunhee KimICLR 2020 · 179 citations
  2. Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge GraphsHouyu Zhang, Zhenghao Liu, Chenyan Xiong, Zhiyuan LiuACL 2020 · 125 citations
  3. Low-Resource Knowledge-Grounded Dialogue GenerationXueliang Zhao, Wei Wu, Chongyang Tao, Can Xu et al.ICLR 2020 · 115 citations
  4. Diverse and Informative Dialogue Generation with Context-Specific Commonsense Knowledge AwarenessSixing Wu, Ying Li, Dawei Zhang, Yang Zhou et al.ACL 2020 · 104 citations
  5. Topic-Aware Multi-turn Dialogue ModelingYi Xu, Hai Zhao, Zhuosheng ZhangAAAI 2021 · 93 citations

Related papers

  1. More is Better: Enhancing Open-Domain Dialogue Generation via Multi-Source Heterogeneous KnowledgeSixing Wu, Ying Li, Minghui Wang, Dawei Zhang et al.EMNLP 2021 · 15 citations
  2. Improving Knowledge-Aware Dialogue Generation via Knowledge Base Question AnsweringJian Wang, Junhao Liu, Wei Bi, Xiaojiang Liu et al.AAAI 2020 · 52 citations
  3. Multiple Knowledge Syncretic Transformer for Natural Dialogue GenerationXiangyu Zhao, Longbiao Wang, Ruifang He, Ting Yang et al.WWW 2020 · 27 citations
  4. Aligning Multiple Knowledge Graphs in A Single PassYaming Yang, Zhe Wang, Ziyu Guan, Wei Zhao et al.WWW 2026 · 5 citations
  5. Achieving Conversational Goals with Unsupervised Post-hoc Knowledge InjectionBodhisattwa Prasad Majumder, Harsh Jhamtani, Taylor Berg-Kirkpatrick, Julian J. McAuleyACL 2022 · 9 citations
Dusk over the sea between two cliffs drawn in fine vertical lines