%0 Conference Proceedings %T CFO: A Framework for Building Production NLP Systems %A Chakravarti, Rishav %A Pendus, Cezar %A Sakrajda, Andrzej %A Ferritto, Anthony %A Pan, Lin %A Glass, Michael %A Castelli, Vittorio %A Murdock, J. William %A Florian, Radu %A Roukos, Salim %A Sil, Avi %Y Padó, Sebastian %Y Huang, Ruihong %S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations %D 2019 %8 November %I Association for Computational Linguistics %C Hong Kong, China %F chakravarti-etal-2019-cfo %X 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 Com- prehension) 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. Screencast links: - Short video (\textless 3 min): http: //ibm.biz/gaama_demo - Supplementary long video (\textless 13 min): http://ibm.biz/gaama_cfo_demo %R 10.18653/v1/D19-3006 %U https://aclanthology.org/D19-3006 %U https://doi.org/10.18653/v1/D19-3006 %P 31-36