top of page

Open Plaza Talk

EVA by App2Check: Build a Cognitive Chatbot With No Technical Skills and Maintain its Knowledge Base as a CMS

Traditional Machine Learning approaches for building cognitive chatbots need technical skills for applying supervised learning/NLP and a lot of effort to train hundreds of intents by providing, for each intent, many examples of questions. Moreover, a small change in the knowledge base requires again technical people and time to retrain and deliver even small updates. EVA by App2Check is a chatbot platform that allows to build cognitive chatbots with no technical skills and to maintain the chatbot Knowledge Base (KB) like a CMS for a website. The implemented methodology allows to start with a fully unsupervised approach and then to focus just on the improvements needed. Our solution also allows to search for both answers in the KB and indexed documents. EVA can be easily integrated with any Dialog Manager and is natively integrated with EngageOne Converse by Pitney Bowes.

June 26

5 mins


Emanuele Di Rosa

Emanuele Di Rosa

Chief Technology Officer, App2Check

Copy of BRN19 Logos for company page- 45

Dr. Di Rosa is currently Chief Technology Officer at App2Check srl, a company dedicated to design and develop AI & NLP-based software, specifically EVA, a platform for building Cognitive Chatbots, and App2Check, a Customer Experience Analytics platform. He has a strong background in Artificial Intelligence, on both the Symbolic approaches to AI, more specifically in Automated Reasoning, developed working with prof. Enrico Giunchiglia and prof. Barry O’Sullivan, and on the ones based on Machine Learning and sub-symbolic representations. He is also co-author of a patent pending titled “System and method for extracting information from unstructured or semi-structured textual sources” which allows EVA platform to transform an FAQ into a domain-based Chatbot in few seconds. He is co-author of 20 scientific papers published by international peer-reviewed international journals/conferences/workshops/doctoral consortiums. Recently, he is more focused on Sentiment Analysis, Text Classification and Machine Learning. In this latter fields, he was speaker at the 2017 Sentiment Analysis Symposium in New York and 2019 CX Emotion conference in London, in the board of the ESWC-17 Challenge on Semantic Sentiment Analysis and won the irony detection task at Evalita SentiPolc 2016 and Ironita 2018. He was speaker and reviewer in many research conferences and workshops and recently technical reviewer in ACL 2018 e ACL 2019. He works on cognitive chatbots since 2004 and was awarded in 2005 by Confindustria Liguria for his chatbot project involving the use of Latent Semantic Analysis for man-machine dialogue.


bottom of page