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

In this paper, we explore the ways to improve POS-tagging using various typesof auxiliary losses and different word representations. As a baseline, weutilized a BiLSTM tagger, which is able to achieve state-of-the-art results onthe sequence labelling tasks. We developed a new method for character-levelword representation using feedforward neural network. Such representation gaveus better results in terms of speed and performance of the model. We alsoapplied a novel technique of pretraining such word representations withexisting word vectors. Finally, we designed a new variant of auxiliary loss forsequence labelling tasks: an additional prediction of the neighbour labels.Such loss forces a model to learn the dependencies in-side a sequence of labelsand accelerates the process of training. We test these methods on English andRussian languages.

Improving part-of-speech tagging via multi-task learning and character-level word representations