This gave me an idea: decades ago I became interested in a natural language processing theory known as Conceptual Dependency Theory (never was very useful to me though, and I was like a dinosaur caught in a tar pit: my fascination with the theory kept me in a stuck state).
Anyway, CDT attempts to extract structured information from text and I thought that if CDT worked, then you could measure something Alex talked about in the article: rating text as interesting if it introduced novel concepts.
Anyway, CDT attempts to extract structured information from text and I thought that if CDT worked, then you could measure something Alex talked about in the article: rating text as interesting if it introduced novel concepts.