Natural language processing is no free lunch

S. Wagner    University of Stuttgart, Stuttgart, Germany


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.


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 O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.