AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Dynamic Knowledge Routing Network for Target-Guided Open-Domain Conversation

Jinghui Qin, Zheng Ye, Jianheng Tang, Xiaodan Liang

AAAI 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain text and graph transfer · 26 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use DKRN with keyword relation routing and dual target-guided selection instead of KernelTarget-guided dialogue on TGPC · TGPC self-playSucc. (%): 62.56 -> 89.0Improved
Use DKRN with keyword relation routing and dual target-guided selection instead of KernelTarget-guided dialogue on CWC · CWC self-playSucc. (%): 53.2 -> 84.4Improved
Use DKRN instead of KernelDialogue agent · CWC human ratingSmoothness: 2.48 -> 3.22Improved
Use DKRN instead of KernelDialogue agent · CWC human ratingSucc. (%): 58.0 -> 88.0Improved
Use DKRN instead of NeuralKeyword prediction · TGPCRw@1: 0.0708 -> 0.0909Improved
Use DKRN instead of NeuralKeyword prediction · CWCRw@1: 0.0654 -> 0.0680Improved
Use DKRN instead of KernelResponse retrieval · TGPCMRR: 0.6877 -> 0.7110Improved
Use DKRN instead of NeuralResponse retrieval · CWCMRR: 0.7326 -> 0.7533Improved
Use DKRN instead of KernelTarget-guided dialogue · TGPC self-play#Turns: 4.65 -> 5.02Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy