作者: Mattia Atzeni , Maurizio Atzori
关键词:
摘要: This paper discusses a language-independent approach for building smart and easily-extensible personal assistants chatbots. Given natural language utterance, the system extracts formal meaning representation that enables mapping user intent to execution of Java source code. allows both chatbots can be easily extended by overriding implementing simple methods. The matching process between input output code relies on an unsupervised algorithm. Therefore, adding new features final does not require training large datasets queries representation.