Research map / Label-efficient and robust learning / Recognition and long-tail
InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling
Xiaobao Wu, Xinshuai Dong, Thong Nguyen, Chaoqun Liu, Liang-Ming Pan, Anh Tuan Luu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use InfoCTM with mutual-information topic alignment and vocabulary linking instead of NMTM | Cross-lingual topic modeling · EC News | TU: 0.784 -> 0.913 | Improved |
| Use InfoCTM instead of NMTM | Cross-lingual topic modeling · Amazon Review | TU: 0.732 -> 0.923 | Improved |
| Use InfoCTM instead of NMTM | Cross-lingual topic modeling · Rakuten Amazon | CNPMI: 0.009 -> 0.034 | Improved |
| Add CVL to link dictionary translations of embedding-neighbor words (ablation) | InfoCTM · EC News, 25% dictionary | TU: 0.795 -> 0.895 | Improved |
| Add CVL to link dictionary translations of embedding-neighbor words (ablation) | InfoCTM · EC News, 25% dictionary | EN-C accuracy: 0.403 -> 0.472 | Improved |
| Add CVL to link dictionary translations of embedding-neighbor words (ablation) | InfoCTM · EC News, 50% dictionary | TU: 0.862 -> 0.905 | Improved |
| Add CVL to link dictionary translations of embedding-neighbor words (ablation) | InfoCTM · EC News, 50% dictionary | EN-C accuracy: 0.433 -> 0.490 | Improved |
| Add CVL to link dictionary translations of embedding-neighbor words (ablation) | InfoCTM · EC News, 75% dictionary | TU: 0.884 -> 0.909 | Improved |
| Add CVL to link dictionary translations of embedding-neighbor words (ablation) | InfoCTM · EC News, 75% dictionary | EN-C accuracy: 0.476 -> 0.519 | Improved |
| Add CVL to link dictionary translations of embedding-neighbor words (ablation) | InfoCTM · EC News, 100% dictionary | TU: 0.899 -> 0.913 | Improved |
| Add CVL to link dictionary translations of embedding-neighbor words (ablation) | InfoCTM · EC News, 100% dictionary | EN-C accuracy: 0.511 -> 0.545 | Improved |
| Add CVL (ablation) | InfoCTM · EC News, 25% dictionary | CNPMI: 0.035 -> 0.036 | Mixed |
Later papers that compared with this method
1 later accepted paper reports InfoCTM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- GloCTM: Cross-Lingual Topic Modeling via a Global Context Space (AAAI 2026 · better on 6 of 6 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
- GloCTM: Cross-Lingual Topic Modeling via a Global Context Space (AAAI 2026 · similarity 0.91)
- Multilingual Anchoring: Interactive Topic Modeling and Alignment Across Languages (NeurIPS 2018 · similarity 0.88)
- Cross-Lingual Taxonomy Alignment with Bilingual Biterm Topic Model (AAAI 2016 · similarity 0.87)
- Improving Semantic Proximity in English-Centric Information Retrieval through Cross-Lingual Alignment (ICLR 2026 · similarity 0.86)
- CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer (AAAI 2024 · similarity 0.83)
- CAR-Transformer: Cross-Attention Reinforcement Transformer for Cross-Lingual Summarization (AAAI 2024 · similarity 0.83)
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.
