------------------------------------------------------
Comments

 The order of pre-NOM modifiers (requirements 1 to 5) has not yet been
 constrained, but might be handled with a modorder type with bool
 features. On a bare NOM these would be [ ALLOW-POSS +, ALLOW-DEM +,
 ALLOW-CLF +, REQUIRE-DEM-OR-NP - ]. They would control the order of
 allowed modifications:


I think you're making things harder than they need to by treating
the classifiers as independent of the demonstratives or numbers.
That is, I think that when a classifier appears, it always forms
a constituent with the thing immediately preceding it.  

Also, it would be interesting to see how your feature-based proposal
compares to the more type-based proposal I posted on EPost.

 It looks like the poss_rel "possessed" relationship is hooked up to
 "book", but the "possessor" relationship is not hooked up to the
 pronoun. I think I might be missing a coindexing relationship in
 possessive-marker-lex.

Indeed, you've created a poss-lex with a one-place relation as
its semantic contribution.  Linking the subject's INDEX to the 
KEYREL.ARG2 should fix that.  You probably also want to specify
that the KEYREL is an event relation.

 Coverage improved by almost 37 percent (successful parses for 36
 grammatical sentences that failed to parse before). Most of these new
 parses were because of grammar changes to support numeral-classifier
 agreement and possessives.

Yay!  It would be nice if you could use the fine system, though.
Is Knoppix not working for you?


2 test cases failing because a classifier can incorrectly appear without a preceding demonstrative or numeral:

    *wo3 you3 ben3 shu1
    *wei4 lao3shi1 kan4 wo3

1 test case failing because a classifier is incorrectly omitted after a numeral:

    *yi1 lao3shi1 kan4 wo3


As I said above: You want the numerals to *not* be modifiers in their
own right, and to have the clfs require either a numeral or a demonstrative.

