AI Paper Atlas

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

GloCTM: Cross-Lingual Topic Modeling via a Global Context Space

Nguyen Tien Phat, Ngo Vu Minh, Linh Ngo Van, Nguyen Thi Ngoc Diep, Thien Huu Nguyen

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 0 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 L_KL consistency loss (ablation)GloCTM · Amazon ReviewEN-C accuracy: 0.708 -> 0.763Improved
add L_CKA loss (ablation)GloCTM · Amazon ReviewEN-C accuracy: 0.718 -> 0.763Improved
add L_CKA loss (ablation)GloCTM · Amazon ReviewCNPMI: 0.054 -> 0.058Improved
add L_CKA loss (ablation)GloCTM · Amazon ReviewTU: 0.961 -> 0.958No clear effect
use KL loss instead of cosine similarity loss (ablation)GloCTM · Amazon ReviewEN-C accuracy: 0.758 -> 0.763Improved
use KL loss instead of cosine similarity loss (ablation)GloCTM · Amazon ReviewCNPMI: 0.059 -> 0.058No clear effect
add L_KL consistency loss (ablation)GloCTM · Amazon ReviewTU: 0.949 -> 0.958Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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