AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

SPINE: SParse Interpretable Neural Embeddings

Anant Subramanian, Danish Pruthi, Harsh Jhamtani, Taylor Berg-Kirkpatrick, Eduard Hovy

AAAI 2018 · Architectures and efficiency › RNNs and normalization · approach: Sparse dictionary representations · 88 citations (OpenAlex)

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 changedWhereMeasuredEffect
Transform GloVe embeddings with SPINE instead of using the original embeddingsGloVe · Word Intrusion Detectionprecision: 22.97 -> 68.35Improved
Transform word2vec embeddings with SPINE instead of using the original embeddingsword2vec · Word Intrusion Detectionprecision: 26.08 -> 74.83Improved
Add the PSL loss term (λ2 = 1) instead of omitting it (λ2 = 0) (ablation)SPINE · GloVe embeddingssparsity: 22% more sparsityImproved
Add the PSL loss term (λ2 = 1) instead of omitting it (λ2 = 0) (ablation)SPINE · word2vec embeddingssparsity: 67% more sparsityImproved
Add denoising noise to the autoencoder (ablation)SPINE · Word embeddingssparsity: 6% more sparseImproved
Use the ASL and PSL combination instead of an ℓ1 sparsity regularizer (ablation)SPINE · Word embeddingsautomated topic coherenceImproved
Increase the hidden dimension size to 2000 or more (ablation)SPINE · Word embeddingsdownstream task performanceHurt
Reduce the hidden dimension size to 500 (ablation)SPINE · Word embeddingsinterpretabilityHurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy