Question Answering System using Knowledge Graphs

A question answering system aims to answer the asked question with relevant responses thus sufficing the re-quested query asked in natural language by responding in the same language. Knowledge Graph Question Answering (KGQA) aims to answer questions asked by the user on a paragraph from a knowledge graph (KG). A strongly connected KG is essential in picking out answers for the requested question. This is because the KG is traversed to select the answer. A well connected KG thus provides a relevant answer. The knowledge graph is built by identifying the subject, the object and the relation for every sentence in the input text or knowledge base. Questions are processed to identify the source-relation-target triples which are then matched with that of the triples forming the KG. The challenge is in extracting the entities and relations between them to create the KG. The model's performance is directly proportional to the strength of the KG. Hence, the presence of a well connected KG provides great accuracy while a poorly connected one would break the system. The proposed model is tested on a Multi RC dataset. Multi RC is a dataset for multi hop question answering that includes short paragraphs and multi-sentence questions. This allows catering to both single hop and multi hop questions. The primary objective was to build a question answering system with the ability to answer multi hop questions together with an efficient response time through the usage of knowledge graphs. A novel approach has been employed where natural language questions are processed into key-value pairs, by leveraging python modules whose dependencies aid in parts of speech tagging in the English language thereby mapping back to the data entities present in the KG to retrieve the correct answer.