Research map / Label-efficient and robust learning / Recognition and long-tail
Multilingual Anchoring: Interactive Topic Modeling and Alignment Across Languages
Michelle Yuan, Benjamin Van Durme, Jordan L Ying
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 |
|---|---|---|---|
| anchor-based multilingual topics instead of generative MCTA | Multilingual anchoring · Wikipedia EN-ZH | English intra-lingual F1: 51.56% -> 69.49% | Improved |
| anchor-based multilingual topics instead of MCTA | Multilingual anchoring · Amazon EN-ZH | English intra-lingual F1: 49.53% -> 59.79% | Improved |
| anchor-based multilingual topics instead of MCTA | Multilingual anchoring · LORELEI EN-SI | classification F1 and coherence: 12.99% -> 20.78% F1; 0.132 -> 0.077 coherence (English) | Mixed |
| anchor-based algorithm instead of MCTA, convergence time | Multilingual anchoring · Wikipedia EN-ZH | time to converge: 5 hours 18 minutes -> within 5 minutes | Improved |
| add interactive human anchor refinement (best user) (ablation) | Multilingual anchoring · Wikipedia EN-ZH | English intra-lingual F1: 69.49% -> 80.71% | Improved |
| add interactive human anchor refinement (median user) (ablation) | Multilingual anchoring · Wikipedia EN-ZH | English intra-lingual F1: 69.49% -> 69.49% | No clear effect |
Closest papers by meaning
- InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling (AAAI 2023 · similarity 0.88)
- Improving Semantic Proximity in English-Centric Information Retrieval through Cross-Lingual Alignment (ICLR 2026 · similarity 0.86)
- GloCTM: Cross-Lingual Topic Modeling via a Global Context Space (AAAI 2026 · similarity 0.86)
- Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining (NeurIPS 2025 · similarity 0.82)
- In-Context Pretraining: Language Modeling Beyond Document Boundaries (ICLR 2024 · similarity 0.82)
- MMTEB: Massive Multilingual Text Embedding Benchmark (ICLR 2025 · similarity 0.82)
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.
