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

The biggest challenge of building chatbots is training data. The requireddata must be realistic and large enough to train chatbots. We create a tool toget actual training data from Facebook messenger of a Facebook page. After textpreprocessing steps, the newly obtained dataset generates FVnC and Sampledataset. We use the Retraining of BERT for Vietnamese (PhoBERT) to extractfeatures of our text data. K-Means and DBSCAN clustering algorithms are usedfor clustering tasks based on output embeddings from PhoBERT$_{base}$. We applyV-measure score and Silhouette score to evaluate the performance of clusteringalgorithms. We also demonstrate the efficiency of PhoBERT compared to othermodels in feature extraction on the Sample dataset and wiki dataset. AGridSearch algorithm that combines both clustering evaluations is also proposedto find optimal parameters. Thanks to clustering such a number ofconversations, we save a lot of time and effort to build data and storylinesfor training chatbot.

Clustering Vietnamese Conversations From Facebook Page To Build Training Dataset For Chatbot