Natural language processing is no free lunch
S. Wagner University of Stuttgart, Stuttgart, Germany
Abstract
Today’s operating systems, with their personal assistants Siri or Cortana, show the impressive progress natural language processing (NLP) has made. They make it seem like all technical and methodological challenges of NLP have been solved. As many artefacts in software engineering are full of natural language, the applications are endless. As it turns out, however, using NLP is no free lunch. We offer a brief check on how and how not to apply NLP in software analytics in this chapter.
Keywords
Natural language processing (NLP); Part-of-speech tagging; Topic modeling; Stemming; Level of abstraction; Clones
Get Perspectives on Data Science for Software Engineering 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.
