Question answering system for chemistry—A semantic agent extension

This paper introduces an extension of a previously developed question answering (QA) system for chemistry, operating on knowledge graph (KG) called Marie. enables the automatic invocation semantic agents to answer questions when static data is absent from KG. The are semantically described using agent ontology, OntoAgent, enable automated discovery and invocation. natural language processing (NLP) models QA need be trained in order interpret answered by new agents. For this purpose, we extend OntoAgent so that it becomes possible automatically create training material NLP models. We evaluate extended with two example chemistry-related evaluation set. result shows allows discover suitable invoke constructing requests description, thereby increasing range can answer.