atlas

Research map / Architectures and efficiency / Attention and transformers

Hierarchical Attention Flow for Multiple-Choice Reading Comprehension

AAAI 2018 · Architectures and efficiency › Attention and transformers · approach: Sparse and structured attention · 76 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 O2P attention (options used to gather evidence) (ablation)Hierarchical Attention Flow · RACE devaccuracy: 46.2 -> 47.2Helped
add O2P attention (options used to gather evidence) (ablation)Hierarchical Attention Flow · RACE-M devaccuracy: 43.7 -> 45.3Helped
add option correlations (ablation)Hierarchical Attention Flow · RACE devaccuracy: 46.5 -> 47.2Helped
add sentence context encoder (ablation)Hierarchical Attention Flow · RACE devaccuracy: 46.9 -> 47.2Helped
add sentence context encoder (ablation)Hierarchical Attention Flow · RACE-M devaccuracy: 45.5 -> 45.3No clear effect
use model vs GA Reader at same 300D embeddingsGA Reader · RACE testaccuracy: 43.9 -> 46.0Helped

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