Research map / Label-efficient and robust learning / Recognition and long-tail
Dirichlet Multinomial Mixture with Variational Manifold Regularization: Topic Modeling over Short Texts
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add variational manifold regularization to DMM | LapDMM · Trec | clustering NMI: 0.125±0.06 -> 0.288±0.04 | Helped |
| add variational manifold regularization to DMM | LapDMM · StackOverFlow | clustering ACC: 0.494±0.03 -> 0.710±0.05 | Helped |
| add variational manifold regularization to DMM | LapDMM · Trec classification K=60 | accuracy: 0.696±0.02 -> 0.852±0.01 | Helped |
| add variational manifold regularization to DMM | LapDMM · Trec K=50 | topic coherence: 0.46±0.07 -> 0.49±0.08 | Helped |
| measure document similarity with word mover's distance instead of cosine on term space (ablation) | LapDMM · Snippets clustering | ACC: 0.761±0.06 -> 0.793±0.03 | Helped |
| measure document similarity with WMD instead of cosine (ablation) | LapDMM · Trec classification K=40 | accuracy: 0.772±0.01 -> 0.844±0.01 | Helped |
| measure document similarity with WMD instead of cosine (ablation) | LapDMM · Trec clustering | ACC: 0.499±0.05 -> 0.484±0.05 | Hurt |
| LapDMM vs BTM on topic coherence | LapDMM · StackOverFlow K=25 | topic coherence: 0.40±0.07 -> 0.39±0.09 | Hurt |
| increase number of nearest neighbors R (ablation) | LapDMM · Trec/Snippets/StackOverFlow | clustering and classification | Helped |
| increase Newton learning rate rho (ablation) | LapDMM · datasets | clustering and classification | No clear effect |
Closest papers by meaning
- OTLDA: A Geometry-aware Optimal Transport Approach for Topic Modeling (NeurIPS 2020 · similarity 0.87)
- Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings (ICLR 2022 · similarity 0.85)
- Geometric Dirichlet Means Algorithm for topic inference (NeurIPS 2016 · similarity 0.85)
- Autoencoding Variational Inference For Topic Models (ICLR 2017 · similarity 0.85)
- Document Summarization with VHTM: Variational Hierarchical Topic-Aware Mechanism (AAAI 2020 · similarity 0.85)
- FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model (NeurIPS 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.