Research map / Graph learning / Knowledge and temporal graphs
ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
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 |
|---|---|---|---|
| Combine ConceptNet knowledge with word embeddings from text using expanded retrofitting | word embeddings · MEN-3000, Rare Words, MTurk-771, and WordSim-353 | Spearman correlation | Helped |
| Use ConceptNet Numberbatch instead of word2vec embeddings | SAT analogy solving · SAT Analogies | accuracy: .486 -> .561 | Helped |
| Use ConceptNet Numberbatch instead of LexVec | bag-of-vectors story ending selection · Story Cloze Test | accuracy: 59.9% vs 59.4% | No clear effect |
Closest papers by meaning
- SensEmBERT: Context-Enhanced Sense Embeddings for Multilingual Word Sense Disambiguation (AAAI 2020 · similarity 0.88)
- Interpreting Knowledge Graph Relation Representation from Word Embeddings (ICLR 2021 · similarity 0.88)
- MKGL: Mastery of a Three-Word Language (NeurIPS 2024 · similarity 0.88)
- ICLR: In-Context Learning of Representations (ICLR 2025 · similarity 0.87)
- Physics of Language Models: Part 3.1, Knowledge Storage and Extraction (ICML 2024 · similarity 0.86)
- KGGen: Extracting Knowledge Graphs from Plain Text with Language Models (NeurIPS 2025 · similarity 0.86)
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.