AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Be Relevant, Non-Redundant, and Timely: Deep Reinforcement Learning for Real-Time Event Summarization

Min Yang, Chengming Li, Fei Sun, Zhou Zhao, Ying Shen, Chenglin Wu

AAAI 2020 · Architectures and efficiency › Attention and transformers · approach: Language model pretraining and induction · 9 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
add reinforcement learning (ablation)DRES · TREC-RTS-16GMP: -0.102 -> -0.080Improved
add reinforcement learning (ablation)DRES · TREC-RTS-17GMP: -0.094 -> -0.056Improved
add relevance prediction auxiliary task (ablation)DRES · TREC-RTS-16GMP: -0.097 -> -0.080Improved
add relevance prediction auxiliary task (ablation)DRES · TREC-RTS-17GMP: -0.097 -> -0.056Improved
add multi-topic dynamic memory network (ablation)DRES · TREC-RTS-16GMP: -0.091 -> -0.080Improved
add multi-topic dynamic memory network (ablation)DRES · TREC-RTS-17GMP: -0.067 -> -0.056Improved
add context-aware Transformer (ablation)DRES · TREC-RTS-16EG-1: 0.299 -> 0.308Improved
add multi-perspective cross-attention (ablation)DRES · TREC-RTS-17EG-1: 0.295 -> 0.302Improved
add reinforcement learning (ablation)DRES · TREC-RTS-16EG-0: 0.071 -> 0.087Improved
add reinforcement learning (ablation)DRES · TREC-RTS-17Latency: 40182 -> 35319Improved
replace representation and Transformer layers with pre-trained BERT (DRES+Bert)DRES · TREC-RTS-16EG-1: 0.308 -> 0.306No clear effect
replace representation and Transformer layers with pre-trained BERT (DRES+Bert)DRES · TREC-RTS-17EG-1: 0.302 -> 0.298No clear effect

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