AI Paper Atlas

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

GlobalTrait: Personality Alignment of Multilingual Word Embeddings

Farhad Bin Siddique, Dario Bertero, Pascale Fung

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining

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
Use multilingual training with GlobalTrait-aligned embeddings in a two-channel CNN instead of monolingual CNN embeddingsCNN personality classifier · PAN 2015 SpanishF-score (average): 71.1 -> 74.6Improved
Use multilingual training with GlobalTrait-aligned embeddings in a two-channel CNN instead of monolingual CNN embeddingsCNN personality classifier · PAN 2015 ItalianF-score (average): 68.1 -> 68.2Improved
Use multilingual training with GlobalTrait-aligned embeddings in a two-channel CNN instead of monolingual CNN embeddingsCNN personality classifier · PAN 2015 DutchF-score (average): 68.4 -> 77.5Improved
Use multilingual training with GlobalTrait-aligned embeddings instead of monolingual embeddingsCNN personality classifier · Chinese personality corpusF-score (average): 58.8 -> 62.3Improved
Use GlobalTrait-aligned embeddings in CNN regression instead of tf-idf linear regressionPersonality regression · PAN 2015 SpanishRMSE (average): 0.147 -> 0.149Hurt
Use GlobalTrait-aligned embeddings in CNN regression instead of tf-idf linear regressionPersonality regression · PAN 2015 ItalianRMSE (average): 0.124 -> 0.127Hurt
Use GlobalTrait-aligned multilingual embeddings rather than monolingual embeddingsLogistic regression personality classifier · PAN 2015 SpanishF-score (average): 68.2 -> 72.2Improved
Use GlobalTrait-aligned multilingual embeddings rather than monolingual embeddingsLogistic regression personality classifier · PAN 2015 ItalianF-score (average): 58.0 -> 64.1Improved
Use GlobalTrait-aligned multilingual embeddings rather than monolingual embeddingsLogistic regression personality classifier · PAN 2015 DutchF-score (average): 68.8 -> 65.3Hurt
Use multilingual training with GlobalTrait-aligned embeddings in a two-channel CNN instead of monolingual CNN embeddingsCNN personality classifier · PAN 2015 Spanish, Italian, and DutchF-score (average): 71.1 -> 74.6; 68.1 -> 68.2; 68.4 -> 77.5Mixed
Add English training data and GlobalTrait alignment for ChineseMultilingual personality classifier · Chinese personality corpusF-score (average): 57.6 -> 61.9; 58.8 -> 62.3Improved

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