Research map / Label-efficient and robust learning / Recognition and long-tail
AutoSense Model for Word Sense Induction
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 the target-neighbor pair constraint (ablation) | AutoSense · SemEval 2010 | AVG: 23.36 -> 24.59 | Helped |
| Add the switch variable (ablation) | AutoSense · SemEval 2010 | AVG: 22.92 -> 24.59 | Helped |
| Set the number of senses to 100 (ablation) | AutoSense · SemEval 2010 | AVG: 24.59 -> 24.23 | Hurt |
| Tune the number of senses to 5 | AutoSense · SemEval 2010 | AVG: 24.59 -> 25.20 | Helped |
| Add the target-neighbor pair constraint (ablation) | AutoSense · SemEval 2013 | AVG: 20.69 -> 22.16 | Helped |
| Add the switch variable (ablation) | AutoSense · SemEval 2013 | AVG: 21.26 -> 22.16 | Helped |
| Set the number of senses to 100 (ablation) | AutoSense · SemEval 2013 | AVG: 22.16 -> 21.03 | Hurt |
| Add actual additional contexts | AutoSense · SemEval 2013 | AVG: 22.16 -> 24.37 | Helped |
| Increase the configured sense count from 5 to 100 (ablation) | AutoSense · Arnet | Paired F1: 56.2 -> 58.8 | Helped |
| Increase the configured sense count from 5 to 100 (ablation) | AutoSense · PubMed | Paired F1: 44.4 -> 46.5 | Helped |
| Increase the configured sense count from 5 to 100 | STM · PubMed | Paired F1: 44.9 -> 41.9 | Hurt |
Closest papers by meaning
- Leveraging Lexical Substitutes for Unsupervised Word Sense Induction (AAAI 2018 · similarity 0.88)
- SensEmBERT: Context-Enhanced Sense Embeddings for Multilingual Word Sense Disambiguation (AAAI 2020 · similarity 0.88)
- XL-WSD: An Extra-Large and Cross-Lingual Evaluation Framework for Word Sense Disambiguation (AAAI 2021 · similarity 0.87)
- Quantum Interference Model for Semantic Biases of Glosses in Word Sense Disambiguation (AAAI 2024 · similarity 0.84)
- Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words (ICLR 2025 · similarity 0.83)
- Quantum-inspired Non-homologous Representation Constraint Mechanism for Long-tail Senses of Word Sense Disambiguation (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.