Research map / Label-efficient and robust learning / Recognition and long-tail
TC-DWA:Text Clustering with Dual Word-Level Augmentation
Bo Cheng, Ximing Li, Yi Chang
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 anchor-word augmentation (ablation) | TC-DWA · AG News | ACC: 0.810 -> 0.822 | Improved |
| add anchor-word augmentation (ablation) | TC-DWA · DBPedia | ACC: 0.780 -> 0.795 | Improved |
| add anchor-word augmentation (ablation) | TC-DWA · Newsgroup | ACC: 0.477 -> 0.491 | Improved |
| add expectation-word augmentation (ablation) | TC-DWA · AG News | ACC: 0.819 -> 0.822 | Improved |
| add expectation-word augmentation (ablation) | TC-DWA · DBPedia | ACC: 0.784 -> 0.795 | Improved |
| add expectation-word augmentation (ablation) | TC-DWA · Newsgroup | ACC: 0.484 -> 0.491 | Improved |
| add both anchor-word and expectation-word augmentation (ablation) | BERT self-training text clustering · AG News | ACC: 0.808 -> 0.822 | Improved |
| add both anchor-word and expectation-word augmentation (ablation) | BERT self-training text clustering · DBPedia | ACC: 0.776 -> 0.795 | Improved |
| add both anchor-word and expectation-word augmentation (ablation) | BERT self-training text clustering · Newsgroup | ACC: 0.470 -> 0.491 | Improved |
| use BERT layer 12 rather than layer 7 for norm-based attention weights (ablation) | TC-DWA · Newsgroup | ACC: 0.401 -> 0.491 | Improved |
| use BERT layer 12 rather than layer 9 for norm-based attention weights (ablation) | TC-DWA · Newsgroup | ACC: 0.447 -> 0.491 | Improved |
| vary the number of anchor words from 0 to 5 (ablation) | TC-DWA · AG News, DBPedia, and Newsgroup | ACC | Mixed |
Closest papers by meaning
- Deep Clustering of Text Representations for Supervision-Free Probing of Syntax (AAAI 2022 · similarity 0.84)
- Objective-Based Hierarchical Clustering of Deep Embedding Vectors (AAAI 2021 · similarity 0.84)
- Adversarial Word Dilution as Text Data Augmentation in Low-Resource Regime (AAAI 2023 · similarity 0.84)
- Compositional Generalization for Multi-Label Text Classification: A Data-Augmentation Approach (AAAI 2024 · similarity 0.83)
- Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe (NeurIPS 2024 · similarity 0.83)
- Improved Graph Contrastive Learning for Short Text 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.
