nBIIG: A Neural BI Insights Generation System for Table Reporting
This system addresses the need for automated insight generation in Business Intelligence reporting, though it appears incremental as it builds on existing neural and RDF-based methods.
The authors tackled the problem of generating textual insights from tables by developing nBIIG, a neural system that converts tables to RDF representations and uses a trained model to produce fluent insights, which can assist analysts in creating table reports through a human-in-the-loop approach.
We present nBIIG, a neural Business Intelligence (BI) Insights Generation system. Given a table, our system applies various analyses to create corresponding RDF representations, and then uses a neural model to generate fluent textual insights out of these representations. The generated insights can be used by an analyst, via a human-in-the-loop paradigm, to enhance the task of creating compelling table reports. The underlying generative neural model is trained over large and carefully distilled data, curated from multiple BI domains. Thus, the system can generate faithful and fluent insights over open-domain tables, making it practical and useful.