AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

On the Robustness of Text Vectorizers

Rémi Catellier, Samuel Vaiter, Damien Garreau

ICML 2023 · Architectures and efficiency › RNNs and normalization · approach: Non-autoregressive translation · 0 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
Replace up to |S| tokens in a documentConcatenation · Documents of fixed lengthembedding distance: 1/2-HölderImproved
Replace up to |S| tokens in a documentNon-normalized TF-IDF · Documents of fixed lengthembedding distance: 4m_{\max} v_{\max} \frac{\card{\mathcal{S}}}{T}Improved
Replace up to |S| tokens in a documentNormalized TF-IDF · Documents of fixed lengthembedding distance: \frac{4m_{\max}^{1/2}v_{\max}^{1/2}D^{1/4}}{v_{\min}^{1/2}} \sqrt{\frac{\card{\mathcal{S}}}{T}}Improved
Replace a sufficiently small subset of tokensdoc2vec · Documents of fixed lengthembedding distance: L \frac{\card{\mathcal{S}}}{T}Improved
Keep the number of replacements fixed while increasing document lengthdoc2vec · IMDB movie reviewsembedding distance: 1/TImproved

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