Paper: Building Trainable Taggers in a Web-based, UIMA-Supported NLP Workbench

ACL ID P12-3021
Title Building Trainable Taggers in a Web-based, UIMA-Supported NLP Workbench
Venue Annual Meeting of the Association of Computational Linguistics
Session System Demonstration
Year 2012
Authors

Argo is a web-based NLP and text mining workbench with a convenient graphical user interface for designing and executing process- ing workflows of various complexity. The workbench is intended for specialists and non- technical audiences alike, and provides the ever expanding library of analytics compliant with the Unstructured Information Manage- ment Architecture, a widely adopted interop- erability framework. We explore the flexibil- ity of this framework by demonstrating work- flows involving three processing components capable of performing self-contained machine learning-based tagging. The three components are responsible for the three distinct tasks of 1) generating observations or features, 2) train- ing a statistical model based on the generated features, and 3) tagging unlabelled...