Research map / Label-efficient and robust learning / Recognition and long-tail
Verb Class Induction with Partial Supervision
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 partial supervision (SS) to Joint model (ablation) | Joint · VerbNet test set | F1: 48.13 -> 58.61 | Helped |
| add partial supervision to Step-wise model (ablation) | Step-wise · VerbNet test set | F1: 50.69 -> 60.26 | Helped |
| add partial supervision to Joint + slot (ablation) | Joint + slot · VerbNet test set | F1: 52.02 -> 63.96 | Helped |
| add slot features to Joint vocabulary (ablation) | Joint · VerbNet test set | F1: 48.13 -> 52.02 | Helped |
| add slot features to Joint + SS (ablation) | Joint + SS · VerbNet test set | F1: 58.61 -> 63.96 | Helped |
| add partial supervision to Joint (ablation) | Joint · VerbNet test set | mPU: 53.42 -> 64.04 | Helped |
| add partial supervision to Step-wise (ablation) | Step-wise · VerbNet test set | iPU: 54.00 -> 54.70 | No clear effect |
| add partial supervision to Joint (ablation) | Joint · never-observed classes C2 | iPU: 41.76 -> 51.40 | Helped |
| add partial supervision to Joint + slot (ablation) | Joint + slot · never-observed classes C2 | iPU: 42.10 -> 57.99 | Helped |
| add partial supervision to Step-wise (ablation) | Step-wise · never-observed classes C2 | iPU: 55.13 -> 55.84 | No clear effect |
| add partial supervision to Joint (ablation) | Joint · partially-supervised classes C1 | iPU: 47.12 -> 58.23 | Helped |
| seed topic with VerbNet 45.6 examples (ablation) | Joint · VerbNet 45.6 test sentences | sentences grouped: 594 -> 882 | Helped |
Closest papers by meaning
- Bayesian Verb Sense Clustering (AAAI 2018 · similarity 0.92)
- Nemotron-CLIMB: Clustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training (NeurIPS 2025 · similarity 0.85)
- Deep Clustering of Text Representations for Supervision-Free Probing of Syntax (AAAI 2022 · similarity 0.85)
- Clustering Properties of Self-Supervised Learning (ICML 2025 · similarity 0.83)
- Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning (ICML 2025 · similarity 0.83)
- Distilling Structured Rationale from Large Language Models to Small Language Models for Abstractive Summarization (AAAI 2025 · 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.