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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Sentiment analysis is the most basic NLP task to determine the polarity oftext data. There has been a significant amount of work in the area ofmultilingual text as well. Still hate and offensive speech detection faces achallenge due to inadequate availability of data, especially for Indianlanguages like Hindi and Marathi. In this work, we consider hate and offensivespeech detection in Hindi and Marathi texts. The problem is formulated as atext classification task using the state of the art deep learning approaches.We explore different deep learning architectures like CNN, LSTM, and variationsof BERT like multilingual BERT, IndicBERT, and monolingual RoBERTa. The basicmodels based on CNN and LSTM are augmented with fast text word embeddings. Weuse the HASOC 2021 Hindi and Marathi hate speech datasets to compare thesealgorithms. The Marathi dataset consists of binary labels and the Hindi datasetconsists of binary as well as more-fine grained labels. We show that thetransformer-based models perform the best and even the basic models along withFastText embeddings give a competitive performance. Moreover, with normalhyper-parameter tuning, the basic models perform better than BERT-based modelson the fine-grained Hindi dataset.

Hate and Offensive Speech Detection in Hindi and Marathi