AI Paper Atlas

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

Distinguish Polarity in Bag-of-Words Visualization

Yusheng Xie, Zhengzhang Chen, Ankit Agrawal, Alok Choudhary

AAAI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 1 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
concatenate Jaro-Winkler literal similarity E, re-encoded by smooth AE (k=2), to word vectorst-SNE on word vectors · Polarity vocabulary, emotion domain, M=2cross-entropy: .042 -> .021Improved
concatenate re-encoded literal similarity (AE k=2) to word vectorst-SNE on word vectors · Polarity vocabulary, temperature domain, M=2cross-entropy: .078 -> .027Improved
concatenate re-encoded literal similarity (AE k=2) to word vectorst-SNE on word vectors · Polarity vocabulary, size domain, M=5cross-entropy: .309 -> .220Improved
concatenate re-encoded literal similarity (AE k=2) to word vectorst-SNE on word vectors · Polarity vocabulary, gender domain, M=3cross-entropy: .119 -> .062Improved
concatenate re-encoded literal similarity (AE k=2) to word vectorst-SNE on word vectors · Polarity vocabulary, temperature domain, M=3cross-entropy: .025 -> .025No clear effect
concatenate raw [XE] without re-encoding (ablation)t-SNE on word vectors · Polarity vocabulary, size domain, M=4cross-entropy: .175 -> .741Hurt
replace linear PCA by smooth AE (k=2) for re-encoding [XE] (ablation)t-SNE on [XE] · Polarity vocabulary, emotion domain, M=4cross-entropy: .108 -> .035Improved
replace sparse AE (k=1) by smooth AE (k=2) (ablation)t-SNE on [XE] · Polarity vocabulary, gender domain, M=2cross-entropy: .071 -> .060Improved
replace sparse AE (k=1) by smooth AE (k=2) (ablation)t-SNE on [XE] · Polarity vocabulary, temperature domain, M=5cross-entropy: .060 -> .029Improved
replace linear PCA by smooth AE (k=2) (ablation)t-SNE on [XE] · Polarity vocabulary, size domain, M=3cross-entropy: .178 -> .177Improved
raise concentration weight beta with k=0.5 (ablation)AE hidden layer · enwik100 neuron activationsactivation distributionMixed
raise beta with k=2 (ablation)AE hidden layer · enwik100 neuron activationsactivation distributionMixed

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