A Data-Centric Framework for Composable NLP Workflows
This addresses the problem of fragmented development for practitioners in domains like healthcare and finance, though it is incremental as it builds on existing tools and libraries.
The paper tackles the complexity of building NLP systems in application domains by establishing a unified open-source framework for composable workflows, resulting in a modular infrastructure with a large repository of interoperable processors.
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).