AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Heavy-tailed Representations, Text Polarity Classification & Data Augmentation

Hamid Jalalzai, Pierre Colombo, Chloé Clavel, Eric Gaussier, Giovanna Varni, Emmanuel Vignon, Anne Sabourin

NeurIPS 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 7 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
Learn a heavy-tailed representation rather than classify directly on BERT embeddings (ablation)Sentiment classification with LHTR · Amazon and Yelp extreme regionsclassification lossImproved
Add a separate classifier dedicated to extremes (ablation)LHTR · Amazon extremeclassification loss: 0.091 -> 0.08Improved
Add a separate classifier dedicated to extremes (ablation)LHTR · Yelp extremeclassification loss: 0.139 -> 0.1205Improved
Use NN for bulk examples and LHTR for extreme examplesSentiment classification · Amazon overallclassification loss: 0.098 -> 0.084Improved
Use NN for bulk examples and LHTR for extreme examplesSentiment classification · Yelp overallclassification loss: 0.111 -> 0.103Improved
Augment training data with GENELIEXFastText classifier · Amazon mediumF1: 84.0 -> 86.3Improved
Augment training data with GENELIEXFastText classifier · Amazon largeF1: 93.3 -> 94.0Improved
Augment training data with GENELIEXFastText classifier · Yelp mediumF1: 86.7 -> 88.4Improved
Augment training data with GENELIEXFastText classifier · Yelp largeF1: 94.1 -> 94.2Improved
Use GENELIEX instead of synonym-based augmentationText data augmentation · Amazon and Yelpdiversity (dist1/dist2)Improved
Scale an extreme latent code to generate sequencesGENELIEX · Amazon and Yelp sentiment generationsentiment label preservationMixed
Use the unconstrained extreme classifier rather than impose angular structure explicitly (ablation)LHTR extreme classifier · Preliminary classification experimentsclassification performanceImproved

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