Research map / Label-efficient and robust learning / Recognition and long-tail
Inside Out: Two Jointly Predictive Models for Word Representations and Phrase Representations
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 morpheme prediction to CBOW (BEING) | CBOW 300d · RW | Spearman rho x100: 45.19 -> 50.41 | Helped |
| add morpheme prediction to Skip-Gram (SEING) | SG 300d · RW | Spearman rho x100: 45.55 -> 46.86 | Helped |
| add morpheme prediction to CBOW (BEING) | CBOW 300d · SL-999 | Spearman rho x100: 38.82 -> 44.91 | Helped |
| add morpheme prediction to Skip-Gram (SEING) | SG 300d · WS-353 | Spearman rho x100: 70.74 -> 72.09 | Helped |
| add morpheme prediction to CBOW (BEING) | CBOW 300d · Word analogy total | accuracy %: 73.58 -> 77.15 | Helped |
| add morpheme prediction to Skip-Gram (SEING) | SG 300d · Word analogy total | accuracy %: 70.69 -> 74.26 | Helped |
| add morpheme prediction to CBOW (BEING) | CBOW 300d · Syntactic analogy plural-verbs | accuracy %: 65.86 -> 85.86 | Helped |
| add morpheme prediction (BEING/SEING) on adjective-to-adverb | CBOW/SG 300d · Syntactic analogy adjective-to-adverb | accuracy %: 31.85 -> 26.51 | Hurt |
| add morpheme prediction to CBOW (BEING) | CBOW 50d · RW | Spearman rho x100: 40.65 -> 45.92 | Helped |
Closest papers by meaning
- Joint Word Representation Learning Using a Corpus and a Semantic Lexicon (AAAI 2016 · similarity 0.88)
- Learning Context-Specific Word/Character Embeddings (AAAI 2017 · similarity 0.87)
- Geometric Relationship between Word and Context Representations (AAAI 2018 · similarity 0.87)
- By Tying Embeddings You Are Assuming the Distributional Hypothesis (ICML 2024 · similarity 0.86)
- On the Emergence of Linear Analogies in Word Embeddings (NeurIPS 2025 · similarity 0.86)
- The Geometry of Categorical and Hierarchical Concepts in Large Language Models (ICLR 2025 · similarity 0.84)
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.