Research map / Label-efficient and robust learning / Recognition and long-tail
Understanding the Semantic Content of Sparse Word Embeddings Using a Commonsense Knowledge Base
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 |
|---|---|---|---|
| use k-means atoms instead of DLSC | sparse GloVe · ConceptNet base assignment | F-score: 0.105 -> 0.072 | Hurt |
| use GMPO atoms instead of DLSC | sparse GloVe · ConceptNet base assignment | F-score: 0.105 -> 0.117 | No clear effect |
| use k-means instead of DLSC | sparse GloVe · Reconstruction | reconstruction error: 2734.5 -> 3286.9 | Hurt |
| lower regularization lambda from 0.5 to 0.1 (ablation) | DLSC · ConceptNet base assignment | MAP: avg nonzero 52.9 -> 186.9 | Hurt |
| lower regularization lambda from 0.5 to 0.1 (ablation) | DLSC · ConceptNet base assignment | TAB | Helped |
Closest papers by meaning
- Semantic Structure-Based Word Embedding by Incorporating Concept Convergence and Word Divergence (AAAI 2018 · similarity 0.92)
- Learning Semantic Representations for Novel Words: Leveraging Both Form and Context (AAAI 2019 · similarity 0.90)
- Unseen Word Representation by Aligning Heterogeneous Lexical Semantic Spaces (AAAI 2019 · similarity 0.90)
- Learning Context-Specific Word/Character Embeddings (AAAI 2017 · similarity 0.88)
- By Tying Embeddings You Are Assuming the Distributional Hypothesis (ICML 2024 · similarity 0.88)
- Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE) (NeurIPS 2024 · similarity 0.87)
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.