Research map / Probabilistic and scientific modeling / Variational and generative sampling
Dynamic Word Embeddings
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 dynamic skip-gram filtering instead of independently trained static skip-gram | Word embeddings on SoU and Twitter · SoU and Twitter | held-out predictive log-likelihood | Helped |
| Use dynamic skip-gram smoothing instead of dynamic skip-gram filtering | Dynamic skip-gram · Google Books, SoU, and Twitter | held-out predictive log-likelihood | Helped |
| Initialize static skip-gram embeddings with the previous time step's embeddings | Static skip-gram (SGP vs. SGI) · Google Books, SoU, and Twitter | held-out predictive log-likelihood | No clear effect |
| Share information across time with a dynamic prior rather than fitting static models separately | Dynamic skip-gram · SoU and Twitter | embedding trajectory smoothness | Helped |
Closest papers by meaning
- Context Selection for Embedding Models (NeurIPS 2017 · similarity 0.89)
- Word2Fun: Modelling Words as Functions for Diachronic Word Representation (NeurIPS 2021 · similarity 0.89)
- Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models (NeurIPS 2025 · similarity 0.88)
- Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe (NeurIPS 2024 · similarity 0.88)
- Training Temporal Word Embeddings with a Compass (AAAI 2019 · similarity 0.88)
- A Simple but Tough-to-Beat Baseline for Sentence Embeddings (ICLR 2017 · similarity 0.88)
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.