Research Field: Computational Linguistics

Content of Research:

The system is based on a full-fledged NLP pipeline that goes from tokens to the  underlying semantics. Current technologies are using machine learning to create a  chat-bot automatically but in fact their success rate is very low and not at all  guaranteed due to the inability of machine learning to cope with fine-grained  semantic analysis. Features like negation, comparatives and conditionals are out of  the scope of any current pre-trained language model. Our system needs only to  upgrade the basic vocabulary related to the domain. The grammar feeding the  semantics, currently implemented only covers two languages, English and Italian, but  more languages could be added if needed while the semantics will remain the same.

Anticipated Achievements:

It is a tool for Customer Relation Management based on deep semantics  and text understanding and is greatly beneficial for large and small industries, business companies, improving their Customer Service. It can work at the same time  with multiple customers (multitasking) and at any time of the day.