Research map / Label-efficient and robust learning / Semi-supervised learning
Weakly-Supervised Hierarchical Text Classification
Yu Meng, Jiaming Shen, Chao Zhang, Jiawei Han
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 |
|---|---|---|---|
| Add WeSHClass's weak-supervision and hierarchical training approach | WeSHClass · NYT, arXiv, and Yelp Review; keyword and document supervision | Macro-F1 and Micro-F1 | Improved |
| Add the global classifier ensemble instead of greedy local predictions (ablation) | WeSHClass · NYT keywords | Macro-F1: 0.618 -> 0.632 | Improved |
| Add movMF class-semantic modeling for pseudo-document generation (ablation) | WeSHClass · NYT keywords | Macro-F1: 0.628 -> 0.632 | Improved |
| Add global self-training (ablation) | WeSHClass · NYT keywords | Macro-F1: 0.550 -> 0.632 | Improved |
| Add the global classifier ensemble instead of greedy local predictions (ablation) | WeSHClass · NYT docs | Macro-F1: 0.520 (0.065) -> 0.532 (0.015) | Improved |
| Add movMF class-semantic modeling for pseudo-document generation (ablation) | WeSHClass · NYT docs | Macro-F1: 0.527 (0.031) -> 0.532 (0.015) | Improved |
| Add global self-training (ablation) | WeSHClass · NYT docs | Macro-F1: 0.491 (0.036) -> 0.532 (0.015) | Improved |
| Generate pseudo documents with movMF plus an LSTM language model rather than bag-of-words or bag-of-words plus reordering | WeSHClass · NYT keywords, level 1 self-training | performance | Improved |
Closest papers by meaning
- Hierarchical Text Classification as Sub-hierarchy Sequence Generation (AAAI 2023 · similarity 0.88)
- Generative Text Convolutional Neural Network for Hierarchical Document Representation Learning (TPAMI 2022 · similarity 0.85)
- Self-Supervised Learning for Text Recognition: A Critical Survey (IJCV 2025 · similarity 0.84)
- A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification (ICLR 2023 · similarity 0.84)
- Deep Short Text Classification with Knowledge Powered Attention (AAAI 2019 · similarity 0.84)
- Self-Paced Unified Representation Learning for Hierarchical Multi-Label Classification (AAAI 2024 · 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.
