Chapter 16. Combining Natural Language Processing Engines
John F. Pitrelli and Burn L. Lewis
16.1. Introduction
Many early speech and natural language processing (NLP) applications were based on single processing engines, such as a speech-to-text (STT, a.k.a. speech recognition) engine for dictation or a translation engine for text translation. However, many engines are now attaining accuracy sufficient to enable combining them to serve more complex tasks than were possible before, despite the compounding of errors inherent in such a combination. Example applications in the text domain include semantic search, enterprise reporting and other business intelligence, question answering, medical-abstract mining, and crosslingual search. Examples of ...
Get Multilingual Natural Language Processing Applications: From Theory to Practice now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
