AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Neural Knowledge Acquisition via Mutual Attention Between Knowledge Graph and Text

AAAI 2018 · Graph learning › Knowledge and temporal graphs · approach: Inductive knowledge graph completion · 164 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
joint training with KG model (Prob-TransD) and knowledge-based attentionCNN relation extractor · NYT-FB60KP@N mean: 61.5 -> 71.0Helped
joint learning with KG (ablation)CNN+ONE · NYT-FB60KP@N mean: 56.4 -> 62.6Helped
replace sentence-level attention with knowledge-based attention (ablation)JointD · NYT-FB60KP@N mean: 67.7 -> 71.0Helped
use Prob-TransD instead of Prob-TransE as KG model (ablation)Joint+KATT · NYT-FB60KP@N mean: 68.9 -> 71.0Helped
joint learning with text via semantics-based attention (ablation)Prob-TransE · FB15KHits@10: 76.6 -> 79.3Helped
joint learning with text via semantics-based attention (ablation)Prob-TransD · FB15KHits@10: 78.2 -> 80.4Helped
JointD+SATT vs dependency-parsing joint modelKGC · FB15K-237Hits@10: 61.1 -> 69.9Helped

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