Dashboard: An integration and testing platform based on backboard architecture for NLP applications

Abstract

The paper presents a software integration, testing and visualization tool, called Dashboard, which is based on pipe-lined backboard architecture for family of natural language processing (NLP) application. The Dashboard helps in testing of a module in isolation, facilitating the training and tuning of a module, integration and testing of a set of heterogeneous modules, and building and testing of complete integrated system as well. It is also equipped with a user-friendly visualization tool to build, test, and integrate a system (or a subsystem) and view its component-wise performance, and step-wise processing as well. The Dashboard is being successfully used by a consortium of eleven academic institutions to develop a suite of bi-directional machine translation (MT) system for nine pairs of Indic languages, and six MT systems have already been deployed on web. The MT systems are being developed by reusing / re-engineering previously developed NLP modules, by different institutions, in different programming languages, using Dashboard as the testing and integration tool. The paper also discusses the experiences of developing MT products in consortium mode, using Dashboard as its integrating and testing platform, and its proposed enhancements.