[Corpora-List] Language complexity for textual processing

Alon Lischinsky alischinsky at gmail.com
Thu Jan 26 11:10:24 UTC 2012


Hi Taras,

> I wonder if anyone knows a research on language complexity evaluation
> regarding textual processing?

In the last CSLP there was an interesting presentation by Philip
Blache, "Evaluating Language Complexity in Context: New Parameters for
a Constraint-Based Model". It doesn't provide a ranking, but explains
the rationale for a reasonably sophisticated metric of complexity that
can hold across different contexts. You can find it in the online
proceedings at http://control.ruc.dk/CSLP2011/temp/CSLP2011Proceedings.pdf

> Intuitively, I can, for example, assume
> that English is easier for text processing than French because the
> latter is more inflected than English which would require more complex
> lemmatisation.

It all depends on what kind of processing you're interested in.
Anything involving the semantics, let alone the pragmatics, of natural
language in context is so far beyond our ability to process it that
measuring its complexity seems a pointless exercise.

Cheers,

A.

_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora



More information about the Corpora mailing list