Papers with embedding compression
Single Training Dimension Selection for Word Embedding with PCA (D19-1)
Copied to clipboard
| Challenge: | Existing methods for word embeddings are limited by the definition of 'low' dimensionality, which is often used to train word embeds into low dimensional continuous vector space. |
| Approach: | They propose a method to select the number of dimensions for word embeddings using PCA. |
| Outcome: | The proposed method trains one embedding with a generous upper bound (e.g. 1,000) of dimensions and then removes the lesser dimensions one at a time while recording the embeddables’ performance on language tasks. |
Do We Really Need All Those Dimensions? An Intrinsic Evaluation Framework for Compressed Embeddings (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation methods for compressed text embeddings are either expensive or too simplistic. |
| Approach: | They propose a task-agnostic intrinsic evaluation framework that provides a reliable proxy for downstream performance. |
| Outcome: | The proposed framework provides a reliable proxy for downstream performance. |