Automatic Construction of Enterprise Knowledge Base

TL;DR

This paper introduces an automated system for constructing enterprise knowledge bases from large-scale documents, utilizing deep learning and classical machine learning to improve accuracy and efficiency, and demonstrating its deployment in a real-world Microsoft 365 environment.

Contribution

The paper presents a novel integrated approach combining deep learning and classical machine learning for enterprise knowledge base construction from unstructured documents.

Findings

Effective extraction of named entities and definitions from enterprise documents.

Improved knowledge base quality through global statistical processing.

Successful deployment within Microsoft 365 service.

Abstract

In this paper, we present an automatic knowledge base construction system from large scale enterprise documents with minimal efforts of human intervention. In the design and deployment of such a knowledge mining system for enterprise, we faced several challenges including data distributional shift, performance evaluation, compliance requirements and other practical issues. We leveraged state-of-the-art deep learning models to extract information (named entities and definitions) at per document level, then further applied classical machine learning techniques to process global statistical information to improve the knowledge base. Experimental results are reported on actual enterprise documents. This system is currently serving as part of a Microsoft 365 service.