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

In this work, we present the Chatbot Interaction with Artificial Intelligence(CI-AI) framework as an approach to the training of deep learning chatbots fortask classification. The intelligent system augments human-sourced data viaartificial paraphrasing in order to generate a large set of training data forfurther classical, attention, and language transformation-based learningapproaches for Natural Language Processing. Human beings are asked toparaphrase commands and questions for task identification for further executionof a machine. The commands and questions are split into training and validationsets. A total of 483 responses were recorded. Secondly, the training set isparaphrased by the T5 model in order to augment it with further data. Sevenstate-of-the-art transformer-based text classification algorithms (BERT,DistilBERT, RoBERTa, DistilRoBERTa, XLM, XLM-RoBERTa, and XLNet) arebenchmarked for both sets after fine-tuning on the training data for twoepochs. We find that all models are improved when training data is augmented bythe T5 model, with an average increase of classification accuracy by 4.01%. Thebest result was the RoBERTa model trained on T5 augmented data which achieved98.96% classification accuracy. Finally, we found that an ensemble of the fivebest-performing transformer models via Logistic Regression of output labelpredictions led to an accuracy of 99.59% on the dataset of human responses. Ahighly-performing model allows the intelligent system to interpret humancommands at the social-interaction level through a chatbot-like interface (e.g."Robot, can we have a conversation?") and allows for better accessibility to AIby non-technical users.

Chatbot Interaction with Artificial Intelligence: Human Data Augmentation with T5 and Language Transformer Ensemble for Text Classification