English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

This paper describes a preliminary study for producing and distributing alarge-scale database of embeddings from the Portuguese Twitter stream. We startby experimenting with a relatively small sample and focusing on threechallenges: volume of training data, vocabulary size and intrinsic evaluationmetrics. Using a single GPU, we were able to scale up vocabulary size from 2048words embedded and 500K training examples to 32768 words over 10M trainingexamples while keeping a stable validation loss and approximately linear trendon training time per epoch. We also observed that using less than 50\% of theavailable training examples for each vocabulary size might result inoverfitting. Results on intrinsic evaluation show promising performance for avocabulary size of 32768 words. Nevertheless, intrinsic evaluation metricssuffer from over-sensitivity to their corresponding cosine similaritythresholds, indicating that a wider range of metrics need to be developed totrack progress.

Learning Word Embeddings from the Portuguese Twitter Stream: A Study of some Practical Aspects