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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Texts obtained from web are noisy and do not necessarily follow theorthographic sentence and word boundary rules. Thus, sentence segmentation andword tokenization systems that have been developed on well-formed texts mightnot perform so well on unedited web texts. In this paper, we first describe themanual annotation of sentence boundaries of an Estonian web dataset and thenpresent the evaluation results of three existing sentence segmentation and wordtokenization systems on this corpus: EstNLTK, Stanza and UDPipe. While EstNLTKobtains the highest performance compared to other systems on sentencesegmentation on this dataset, the sentence segmentation performance of Stanzaand UDPipe remains well below the results obtained on the more well-formedEstonian UD test set.

Evaluating Sentence Segmentation and Word Tokenization Systems on Estonian Web Texts