atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Mind the Gap: Cross-Lingual Information Retrieval with Hierarchical Knowledge Enhancement

AAAI 2022 · Vision-language and multimodal › Human and embodied modeling · approach: Multimodal retrieval-augmented modeling · 17 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
add multilingual KG information by concatenating it directly with the query, without hierarchical fusionVanilla BERT CLIR · 12 language pairs in MULTI-8NDCGHelped
use hierarchical information fusion instead of direct KG concatenationHIKE · 12 language pairs in MULTI-8NDCGHelped
add entity and neighboring-entity descriptions (ablation)HIKE · EN-ESNDCG@10: 85.39 -> 86.18Helped
add entity and neighboring-entity labels (ablation)HIKE · EN-ESNDCG@10: 85.47 -> 86.18Helped
add neighboring entities (ablation)HIKE · EN-ESNDCG@10: 85.33 -> 86.18Helped
add target-language information (ablation)HIKE · EN-ESNDCG@10: 84.68 -> 86.18Helped
increase the number of KG neighbors (ablation)HIKE · MULTI-8NDCG@10Mixed

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