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/

Global: Zendy Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper presents a novel approach for multi-lingual sentimentclassification in short texts. This is a challenging task as the amount oftraining data in languages other than English is very limited. Previouslyproposed multi-lingual approaches typically require to establish acorrespondence to English for which powerful classifiers are already available.In contrast, our method does not require such supervision. We leverage largeamounts of weakly-supervised data in various languages to train a multi-layerconvolutional network and demonstrate the importance of using pre-training ofsuch networks. We thoroughly evaluate our approach on various multi-lingualdatasets, including the recent SemEval-2016 sentiment prediction benchmark(Task 4), where we achieved state-of-the-art performance. We also compare theperformance of our model trained individually for each language to a varianttrained for all languages at once. We show that the latter model reachesslightly worse - but still acceptable - performance when compared to the singlelanguage model, while benefiting from better generalization properties acrosslanguages.

Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification