atlas

Research map / Graph learning / Knowledge and temporal graphs

Answering Complex Queries in Knowledge Graphs with Bidirectional Sequence Encoders

AAAI 2021 · Graph learning › Knowledge and temporal graphs · approach: Knowledge graph embeddings · 27 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
use bidirectional self-attention over the queryBiQE · FB15K-237-CQMRR: 0.157 -> 0.228Helped
use bidirectional self-attention over the queryBiQE · WN18RR-CQMRR: 0.149 -> 0.150Helped
use bidirectional self-attention over the queryBiQE · BioAUC: 91.0 -> 96.91Helped
remove attention to future query context (ablation)BiQE · FB15K-237-PathsMRR: 0.473 -> 0.421Hurt
remove attention to future query context (ablation)BiQE · FB15K-237-PathsHITS@10: 0.602 -> 0.553Hurt
double GQE embedding dimensions (ablation)GQE · FB15K-237 and NELL-995HITS@3 (Mean): 0.246 -> 0.249; 0.269 -> 0.270No clear effect
answer missing entities jointly rather than one at a time (ablation)BiQE · FB15K-237-PathsMRR: 0.421 -> 0.473Helped
answer missing entities jointly rather than one at a time (ablation)BiQE · FB15K-237-PathsHITS@10: 0.553 -> 0.602Helped

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