AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

EQG-RACE: Examination-Type Question Generation

AAAI 2021 · Large language models › Retrieval and knowledge · approach: Explanatory and multiple-choice QA benchmarks · 42 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 the unified model components to the maxout-pointer baselineMaxout-pointer question generation · EQG-RACEBLEU-4: 4.06 -> 9.09Helped
Add ELMo embeddings (ablation)Unified model · EQG-RACEBLEU-4: 9.09 -> 11.96Helped
Replace ELMo with BERT embeddings (ablation)Unified model · EQG-RACEBLEU-4: 9.09 -> 10.01Helped
Add answer-guided graph (ablation)Unified model · EQG-RACEBLEU-4: 7.43 -> 9.09Helped
Add passage-answer fusion (ablation)Unified model · EQG-RACEBLEU-4: 7.56 -> 9.09Helped
Add key-sentence tagging (ablation)Unified model · EQG-RACEBLEU-4: 7.62 -> 9.09Helped
Add rough-answer tagging (ablation)Unified model · EQG-RACEBLEU-4: 6.32 -> 9.09Helped

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