On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “meta-embeddings”

Angular-Based Word Meta-Embedding Learningcs.CL

This work compares meta-embeddings for natural language processing tasks.

problem Improving distributed word representations in natural language processing.

method Meta-embeddings trained with angular and normalized distance loss functions compared to standard loss functions.

result Normalization methods outperform standard loss functions on word similarity datasets.

word embeddings meta-learning natural language processing angular distance normalized distance

2018-08-13abs ↗pdf ↗

Gaussian meta-embeddings for efficient scoring of a heavy-tailed PLDA modelstat.ML

Meta-embeddings improve PLDA model's accuracy for speaker recognition.

problem Improving PLDA model's accuracy for speaker recognition.

method Proposed Gaussian meta-embeddings (GMEs) for heavy-tailed PLDA models.

result GMEs with variable precisions propagate uncertainty, leading to up to 20% more accurate results.

meta-embeddings PLDA speaker recognition uncertainty accuracy

2018-02-27abs ↗pdf ↗

Learning Geometric Word Meta-Embeddingscs.CL

Geometrically transforms word embeddings into a common space for better comparison.

problem Comparing embeddings from different sources is challenging.

method Applies orthogonal rotations and Mahalanobis scaling to transform embeddings into a shared latent space.

result The method improves word similarity and analogy tasks.

word embeddings geometric transformations latent space word similarity word analogy

2020-04-20abs ↗pdf ↗

Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddingscs.LG

Meta-Embedding improves CTR predictions for new ads, addressing cold-start and warm-up issues.

problem Improving CTR predictions for new ads with little logging data.

method Meta-learning approach to generate initial embeddings for new ad IDs.

result Meta-Embedding significantly improves CTR predictions for various models, including lightweight and deep learning.

CTR prediction cold-start problem warm-up phase meta-learning embedding generation

2019-04-25abs ↗pdf ↗

Towards Cross-Granularity Few-Shot Learning: Coarse-to-Fine Pseudo-Labeling with Visual-Semantic Meta-Embeddingcs.CV

Paper tackles cross-granularity few-shot learning with meta-embedder.

problem Few-shot learning with coarse labels and fine-grained testing.

method Meta-embedder that optimizes visual and semantic discrimination across coarse and fine classes.

result Meta-embedder achieves effective cross-granularity few-shot classification.

few-shot learning cross-granularity meta-learning pseudo-labeling visual-semantic

2020-07-11abs ↗pdf ↗