AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Relatedness and TBox-Driven Rule Learning in Large Knowledge Bases

Giuseppe Pirrò

AAAI 2020 · Large language models › Retrieval and knowledge · approach: Knowledge graph reasoning with LLMs · 14 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
TBox-driven relatedness-ranked rule learning (RARL) vs best baseline on link predictionRARL · YAGOhits@10: 67.3 -> 69.3Improved
RARL on schema-poor KB vs competitorsRARL · WN-18RR link predictionhits@1: 35.1 vs 44.1 (AnyBURL)Hurt
RARL vs anyBURL and RLvLR on DBpedia rule learningRARL · DBpedianumber of high quality rules: 3564 vs 3246 (anyBURL), 183 (RLvLR)Improved
automata-based traversal query verification instead of conjunctive SPARQL queries (ablation)RARL · DBpedia, d<=3TConf (confidence time): 418.2 -> 121.4Improved
increase related predicates considered (topPs=20 vs 10) (ablation)RARL · FB15K-237hits@1: -7.5Hurt
increase number of examples (nExs=100% vs 80%) (ablation)RARL · FB15K-237hits@1: +0.3No clear effect
restrict to topPs=5, nExs=80%, topC=50% (ablation)RARL · DBpediarunning time (min): 138 -> 58Improved

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