Graph NLU enabled question answering system

Abstract

With a huge amount of information being stored as structured data, there is an increasing need for retrieving exact answers to questions from tables. Answering natural language questions on structured data usually involves semantic parsing of query to a machine understandable format which is then used to retrieve information from the database. Training semantic parsers for domain specific tasks is a tedious job and does not guarantee accurate results. In this paper, we used conversational analytics tool to create the user interface and to get the required entities and intents from the query thus avoiding the traditional semantic parsing approach. We then make use of Knowledge Graph for querying in structured data domain. Knowledge graphs can be easily leveraged for question answering systems, to use them as the database. We extract appropriate answers for different types of queries which have been illustrated in the Results section.

Deep Learning Based Question Answering System (Survey)

“…With this method, a graph of objects and their characteristics is created, with the points denoting the entities in question and the edges denoting their features. The method then employs this graph to provide answers to queries by navigating it and looking for the required response depending on the query entities [45]. This method has the drawback of requiring a lot of data to build the graph, which can be time-consuming and costly computationally [46].…”

A Detailed Study on Aggregation Methods used in Natural Language Interface to Databases (NLIDB)

“…On the other hand [5,6], some user needs might be addressed by something different than a standard querying system. For example, traditional query languages cannot adequately represent the requirements' attributes.…”