Old School Natural Language Processing: Still Around, Of Course
January 12, 2015
I you are a fan of sentiment analysis and the other dark magic of content processing systems, you will find “What Happened to Old School NLP?” worth a moment.
The write up explains a couple of decades of innovation with a reference to the hand- crafting of word lists. The write up points out:
NLP research is now, essentially, just a branch of machine learning rather than a branch of linguistics.
The point that I noted was, “Money.”
The article then talks about sentiment analysis, primitive semantics, and prognostication.
The write up ends in a surprising way:
As AI and NLP become more and more prominent, and as comprehension and reasoning become important tasks, the kinds of structural information that is used for learning will become richer and richer. We’ll start to see the re-emergence of tools from old-school NLP, but now augmented with the powerful statistical tools and data-oriented automation of new-school NLP. IBM’s Watson already does this to some extent.
Ah, IBM Watson.
Stephen E Arnold, January 12, 2015
Comments
-
- Subscribe to Beyond Search
Feature archive
News archive
-
