Research map / Label-efficient and robust learning / Recognition and long-tail
CoVeR: Learning Covariate-Specific Vector Representations with Tensor Decompositions
Kevin Tian, Teng Zhang, James Zou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 joint CoVeR covariate-specific embeddings instead of S-EFE | Word embeddings for Harry Potter books · Harry Potter books | cluster purity (AP): 0.1289 -> 0.1602 | Improved |
| Use joint CoVeR covariate-specific embeddings instead of GloVe | Word embeddings for Harry Potter books · Harry Potter books | cluster purity (AP): 0.1297 -> 0.1602 | Improved |
| Use joint CoVeR covariate-specific embeddings instead of S-EFE | Word embeddings for Harry Potter books · Harry Potter books | cluster purity (BLESS): 0.1942 -> 0.2185 | Improved |
| Use joint CoVeR covariate-specific embeddings instead of GloVe | Word embeddings for Harry Potter books · Harry Potter books | cluster purity (BLESS): 0.2042 -> 0.2185 | Improved |
| Use joint CoVeR covariate-specific embeddings instead of S-EFE | Word embeddings for Harry Potter books · Harry Potter books | cluster purity (Battig): 0.0745 -> 0.0877 | Improved |
| Use joint CoVeR covariate-specific embeddings instead of GloVe | Word embeddings for Harry Potter books · Harry Potter books | cluster purity (Battig): 0.0770 -> 0.0877 | Improved |
| Use joint CoVeR covariate-specific embeddings instead of S-EFE | Word embeddings for Harry Potter books · Harry Potter books | correlation similarity (MEN): 0.0184 -> 0.1370 | Improved |
| Use joint CoVeR covariate-specific embeddings instead of GloVe | Word embeddings for Harry Potter books · Harry Potter books | correlation similarity (MEN): 0.0593 -> 0.1370 | Improved |
| Use joint CoVeR covariate-specific embeddings instead of S-EFE | Word embeddings for Harry Potter books · Harry Potter books | correlation similarity (MTurk): 0.0986 -> 0.0719 | Hurt |
| Use joint CoVeR covariate-specific embeddings instead of GloVe | Word embeddings for Harry Potter books · Harry Potter books | correlation similarity (MTurk): 0.0341 -> 0.0719 | Improved |
| Use joint CoVeR covariate-specific embeddings instead of S-EFE | Word embeddings for Harry Potter books · Harry Potter books | correlation similarity (RG65): -0.0098 -> 0.1272 | Improved |
| Use joint CoVeR covariate-specific embeddings instead of GloVe | Word embeddings for Harry Potter books · Harry Potter books | correlation similarity (RG65): 0.0133 -> 0.1272 | Improved |
Closest papers by meaning
- Understanding Composition of Word Embeddings via Tensor Decomposition (ICLR 2019 · similarity 0.87)
- Active Discriminative Text Representation Learning (AAAI 2017 · similarity 0.86)
- Invariance and identifiability issues for word embeddings (NeurIPS 2019 · similarity 0.86)
- A Simple but Tough-to-Beat Baseline for Sentence Embeddings (ICLR 2017 · similarity 0.85)
- Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe (NeurIPS 2024 · similarity 0.84)
- Harnessing the Universal Geometry of Embeddings (NeurIPS 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.
