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

In this paper, we describe DeFactoNLP, the system we designed for the FEVER2018 Shared Task. The aim of this task was to conceive a system that can notonly automatically assess the veracity of a claim but also retrieve evidencesupporting this assessment from Wikipedia. In our approach, the Wikipediadocuments whose Term Frequency-Inverse Document Frequency (TFIDF) vectors aremost similar to the vector of the claim and those documents whose names aresimilar to those of the named entities (NEs) mentioned in the claim areidentified as the documents which might contain evidence. The sentences inthese documents are then supplied to a textual entailment recognition module.This module calculates the probability of each sentence supporting the claim,contradicting the claim or not providing any relevant information to assess theveracity of the claim. Various features computed using these probabilities arefinally used by a Random Forest classifier to determine the overalltruthfulness of the claim. The sentences which support this classification arereturned as evidence. Our approach achieved a 0.4277 evidence F1-score, a0.5136 label accuracy and a 0.3833 FEVER score.

DeFactoNLP: Fact Verification using Entity Recognition, TFIDF Vector Comparison and Decomposable Attention