# CFO: A Framework for Building Production NLP Systems

## TL;DR

This paper presents CFO, a comprehensive framework for developing, testing, and deploying production-ready NLP and IR systems, demonstrated through a high-quality question answering system utilizing BERT-based models.

## Contribution

The paper introduces CFO, a novel orchestration framework that streamlines building and deploying interactive NLP systems, with a practical demonstration using a BERT-based question answering system.

## Key findings

- High-quality answer retrieval in academic and industry settings
- Effective integration of BERT-based MRC with IR components
- Discussion of best practices for training BERT models for production

## Abstract

This paper introduces a novel orchestration framework, called CFO (COMPUTATION FLOW ORCHESTRATOR), for building, experimenting with, and deploying interactive NLP (Natural Language Processing) and IR (Information Retrieval) systems to production environments. We then demonstrate a question answering system built using this framework which incorporates state-of-the-art BERT based MRC (Machine Reading Comprehension) with IR components to enable end-to-end answer retrieval. Results from the demo system are shown to be high quality in both academic and industry domain specific settings. Finally, we discuss best practices when (pre-)training BERT based MRC models for production systems.