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

Customer service chatbots are conversational systems designed to provideinformation to customers about products/services offered by differentcompanies. Particularly, intent recognition is one of the core components inthe natural language understating capabilities of a chatbot system. Among thedifferent intents that a chatbot is trained to recognize, there is a set ofthem that is universal to any customer service chatbot. Universal intents mayinclude salutation, switch the conversation to a human agent, farewells, amongothers. A system to recognize those universal intents will be very helpful tooptimize the training process of specific customer service chatbots. We proposethe development of a universal intent recognition system, which is trained torecognize a selected group of 11 intents that are common in 28 differentchatbots. The proposed system is trained considering state-of-the-artword-embedding models such as word2vec and BERT, and deep classifiers based onconvolutional and recurrent neural networks. The proposed model is able todiscriminate between those universal intents with a balanced accuracy up to80.4\%. In addition, the proposed system is equally accurate to recognizeintents expressed both in short and long text requests. At the same time,misclassification errors often occurs between intents with very similarsemantic fields such as farewells and positive comments. The proposed systemwill be very helpful to optimize the training process of a customer servicechatbot because some of the intents will be already available and detected byour system. At the same time, the proposed approach will be a suitable basemodel to train more specific chatbots by applying transfer learning strategies.

One System to Rule them All: a Universal Intent Recognition System for Customer Service Chatbots