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 present two deep-learning systems that competed atSemEval-2018 Task 3 "Irony detection in English tweets". We design and ensembletwo independent models, based on recurrent neural networks (Bi-LSTM), whichoperate at the word and character level, in order to capture both the semanticand syntactic information in tweets. Our models are augmented with aself-attention mechanism, in order to identify the most informative words. Theembedding layer of our word-level model is initialized with word2vec wordembeddings, pretrained on a collection of 550 million English tweets. We didnot utilize any handcrafted features, lexicons or external datasets as priorinformation and our models are trained end-to-end using back propagation onconstrained data. Furthermore, we provide visualizations of tweets withannotations for the salient tokens of the attention layer that can help tointerpret the inner workings of the proposed models. We ranked 2nd out of 42teams in Subtask A and 2nd out of 31 teams in Subtask B. However,post-task-completion enhancements of our models achieve state-of-the-artresults ranking 1st for both subtasks.

NTUA-SLP at SemEval-2018 Task 3: Tracking Ironic Tweets using Ensembles of Word and Character Level Attentive RNNs