atlas

Research map / Learning theory and algorithms / Optimal transport

Neural Topic Model via Optimal Transport

ICLR 2021 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 5 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
use NSTM instead of ProdLDA20NG document representations · 20NGtop-Purity: 0.417$\pm$0.004 -> 0.477$\pm$0.011Helped
use NSTM instead of LDAWS document representations · WStop-Purity: 0.446$\pm$0.022 -> 0.451$\pm$0.009Helped
use NSTM instead of ETMTMN document representations · TMNtop-Purity: 0.556$\pm$0.022 -> 0.637$\pm$0.010Helped
use NSTM instead of ProdLDA20NG document representations · 20NGtop-NMI: 0.321$\pm$0.004 -> 0.415$\pm$0.012Helped
use NSTM instead of LDAWS document representations · WStop-NMI: 0.185$\pm$0.013 -> 0.201$\pm$0.004Helped
use NSTM instead of ETMTMN document representations · TMNtop-NMI: 0.328$\pm$0.010 -> 0.334$\pm$0.004No clear effect
combine Sinkhorn distance with expected log-likelihood (ablation)NSTM topic quality and document representations · 20NGTC, TD, top-Purity, top-NMI, km-Purity, km-NMIMixed

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