[developers] Punctuation and "-default-les" type mapping in PET/ERG

[R. Bergmair]

Hi everyone!



I'm trying to use PET/ERG with the "-default-les" option
to convert SMAFs with tokenizations and POS tags to RMRSs
in a mode that's robust against missing lexical entries.

Now I have the following problem: When a token includes
punctuation, the type mapping doesn't seem to be happening.

Here's an example: The ERG doesn't seem to have the word
"reptile" in its lexicon, but I tag it as "NN2" in the SMAF
input, and I have an appropriate pos-mapping in place in
common.set saying "NN2 $generic_pl_noun".

Now

   Reptiles have no fur.
   No reptiles have fur.

work perfectly well, while,

   All snakes are reptiles.
   Snakes, and other reptiles, have fur.

give me error messages along the lines of

   no lexicon entries for:
 	"reptiles." [NN2]

in PET.



I also have another, possibly unrelated, issue. Which is that,
even for the sentences that do work, I get a lot of odd warning
messages like this:

; WARNING: failed to unify new path-value ( = "No") into fs (type: 
d_-_no_le)
; WARNING: failed to unify new path-value ( = "No") into fs (type: 
av_-_s-cp-mc-pr_le)
; WARNING: failed to unify new path-value ( = "No") into fs (type: 
av_-_dg-any_le)
; WARNING: failed to unify new path-value ( = "No") into fs (type: 
av_-_s-cp-nsp-po_le)
; WARNING: failed to unify new path-value ( = "No") into fs (type: 
n_pp_c-nocnh-of_le)
; WARNING: failed to unify new path-value ( = "No") into fs (type: 
n_-_tt-rbst_le)
; WARNING: failed to unify new path-value (SYNSEM.LKEYS.KEYREL.CARG = 
have) into fs (type: v_np-prd_oeq-ntr_le)
; WARNING: failed to unify new path-value (SYNSEM.LKEYS.KEYREL.CARG = 
have) into fs (type: v_np-vpslnp_oeq_le)
; WARNING: failed to unify new path-value (SYNSEM.LKEYS.KEYREL.CARG = 
have) into fs (type: v_np-vp_aeq-prp_le)
; WARNING: failed to create dag for new path-value ( = "fur.")
; WARNING: failed to create dag for new path-value ("reptiles" = 
"reptiles")
; WARNING: failed to create dag for new path-value ("reptiles" = 
"reptiles")
; WARNING: failed to create dag for new path-value ("reptiles" = 
"reptiles")
(1) `no reptiles have fur.' [12288] --- 2 (0.03|0.04s) <22:174> (2051.8K) 
[0.0s]
...

And then I get RMRSs that look perfectly okay. Can I safely ignore
those warnings, or have I done anything wrong in the configuration?



regards,

Richard Bergmair