AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Don't Forget the Quantifiable Relationship between Words: Using Recurrent Neural Network for Short Text Topic Discovery

Heng-Yang Lu, Lu-Yao Xie, Ning Kang, Chong-Jun Wang, Jun-Yuan Xie

AAAI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 35 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 RNN-learned word-relationship and IDF priors to biterm topic modelBTM · Online Questions M=10topic coherence: -116.0 -> -105.3Improved
add RNN-learned word-relationship and IDF priors to biterm topic modelBTM · Online News Titles M=20topic coherence: -639.8 -> -602.4Improved
use biterm-based short text models instead of LDALDA · Online Questions M=10topic coherence: -216.7 -> -116.0Improved
delete topic-irrelevant biterms (d-BTM) instead of BTMBTM · Online Questions M=10topic coherence: -116.0 -> -119.9Hurt
replace biterm deletion (d-BTM) with IDF probabilistic weightingd-BTM · Online News Titles M=20topic coherence: -650.8 -> -602.4Improved
improve RNN perplexity used for prior learning (ablation)RIBS-TM · Online Questionscoherence and clusteringImproved
add RIBS-TM priors for clusteringBTM · Online Questions and News Titlespurity and entropyImproved

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