AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Recurrent Attentional Topic Model

Shuangyin Li, Yu Zhang, Rong Pan, Mingzhi Mao, Yang Yang

AAAI 2017 · Architectures and efficiency › Attention and transformers · approach: State space and recurrent sequence models · 15 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 document-level topic distribution G0 (RATM-D vs RATM-N) (ablation)RATM · Wikipedia T=100perplexity: 402.47 -> 392.05Improved
add document-level topic distribution G0 (RATM-D vs RATM-N) (ablation)RATM · NYTimes T=50perplexity: 576.06 -> 529.08Improved
RATM-D instead of LDA (add recurrent attention over preceding sentences)topic model · Wikipedia T=200perplexity: 402.98 -> 314.47Improved
RATM-D instead of LDAtopic model · NYTimes T=100perplexity: 768.24 -> 442.65Improved
RATM-N instead of LDA (ablation)topic model · Wikipedia T=50perplexity: 585.08 -> 553.87Improved
RATM-D instead of CTMtopic model · Wikipedia T=50perplexity: 524.11 -> 532.72Hurt
increase attention window C from 1 (LDA) to 4 (ablation)RATM-D · Wikipedia T=100perplexity: 424.56 -> 392.05 (C=2 -> C=4)Improved
increase window size C beyond 4 (5, 6) (ablation)RATM-D · Wikipedia T=100perplexity: 392.05 -> 430.15 (C=4 -> C=6)Hurt
increase number of topics from 50 to 200 (ablation)RATM-D · Wikipediaperplexity: 532.72 -> 314.47Improved
RATM-D document embeddings instead of LDA/CTM/RSM/Para2VSVM classifier · Wikipedia and NYTimes classificationprecisionImproved

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