Empirical natural language processing (NLP) systems in application domains (e.g., healthcare, finance, education) involve interoperation among multiple components, ranging from data ingestion, human annotation, to text retrieval, analysis, generation, and visualization. We establish a unified open-source framework to support fast development of such sophisticated NLP workflows in a composable manner. The framework introduces a uniform data representation to encode heterogeneous results by a wide range of NLP tasks. It offers a large repository of processors for NLP tasks, visualization, and annotation, which can be easily assembled with full interoperability under the unified representation. The highly extensible framework allows plugging in custom processors from external off-the-shelf NLP and deep learning libraries. The whole framework is delivered through two modularized yet integratable open-source projects, namely Forte (for workflow infrastructure and NLP function processors) and Stave (for user interaction, visualization, and annotation).
@article{arxiv.2103.01834,
title = {A Data-Centric Framework for Composable NLP Workflows},
author = {Zhengzhong Liu and Guanxiong Ding and Avinash Bukkittu and Mansi Gupta and Pengzhi Gao and Atif Ahmed and Shikun Zhang and Xin Gao and Swapnil Singhavi and Linwei Li and Wei Wei and Zecong Hu and Haoran Shi and Haoying Zhang and Xiaodan Liang and Teruko Mitamura and Eric P. Xing and Zhiting Hu},
journal= {arXiv preprint arXiv:2103.01834},
year = {2021}
}