Merge pull request #2 from delph-in/olzama-dev

Prepare for initial release with Freeling 4.0

README.md

@@ -4,5 +4,5 @@ See the wiki: https://github.com/delph-in/docs/wiki/SrgTop
 
 The Spanish Resource Grammar was developed originally by Montserrat Marimon and her svn repository is http://svn.emmtee.net/trunk/upf/srg .
 
-The LICENSE is the Lesser General Public License For Linguistic Resources.
+The LICENSE is the MIT License.
 

ace/config.tdl

@@ -19,7 +19,95 @@ version                   := "../Version.lsp".
 
 irregular-forms 	  := ../irregs.tab.
 
-quickcheck-code           := "../ace/ace-qc.txt".
+;quickcheck-code           := "../ace/ace-qc.txt".
+
+:begin :instance.
+
+qc_unif_set := *top* &
+[ ARGS.SYNSEM.LOCAL.CAT.HEAD "0" #| 1062708 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.COMPS "1" #| 762446 |#,
+  ARGS.SYNSEM.LOCAL.CAT.HEAD.MOD "2" #| 547322 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.SUBJ "3" #| 335982 |#,
+  ARGS.SYNSEM.LOCAL.CAT.HEAD.KEYS.KEY "4" #| 318034 |#,
+  ARGS.SYNSEM.LOCAL.CAT.MC "5" #| 316814 |#,
+  ARGS.INFLECTED "6" #| 287620 |#,
+  ARGS.SYNSEM.LOCAL.CONT.HOOK.INDEX "7" #| 165854 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.CLTS "8" #| 152099 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.SPR "9" #| 130597 |#,
+  ARGS.SYNSEM.NON-LOCAL.SLASH.LIST "10" #| 120750 |#,
+  ARGS.SYNSEM.LOCAL.CAT.HEAD.MOD.FIRST.LOCAL.CAT.HEAD "11" #| 119531 |#,
+  ARGS.SYNSEM.NON-LOCAL.SLASH "12" #| 112842 |#,
+  ARGS.SYNSEM.LOCAL.CAT.HEAD.MOD.FIRST.LOCAL "13" #| 110827 |#,
+  ARGS.SYNSEM "14" #| 109174 |#,
+  ARGS.SYNSEM.LOCAL.CAT.HEAD.MOD.FIRST.LOCAL.CAT.VAL.SPR "15" #| 100989 |#,
+  ARGS.SYNSEM.LOCAL.AGR.PNG.PN "16" #| 92179 |#,
+  ARGS "17" #| 86641 |#,
+  ARGS.SYNSEM.LOCAL.CONT.RELS.LIST.REST.FIRST.PRED "18" #| 81556 |#,
+  ARGS.SYNSEM.LOCAL.COORD-STRAT "19" #| 77483 |#,
+  ARGS.SYNSEM.LOCAL.CONT.RELS.LIST.FIRST "20" #| 75468 |#,
+  ARGS.SYNSEM.LOCAL.CAT.HEAD.VFORM "21" #| 75277 |#,
+  ARGS.SYNSEM.LOCAL.COORD "22" #| 51355 |#,
+  ARGS.SYNSEM.NON-LOCAL.REL "23" #| 50937 |#,
+  ARGS.SYNSEM.LOCAL.CONT.RELS.LIST.FIRST.PRED "24" #| 44912 |#,
+  ARGS.SYNSEM.LOCAL.CAT.HEAD.KEYS.ALTKEY "25" #| 40093 |#,
+  ARGS.SYNSEM.NON-LOCAL.SLASH.LAST "26" #| 35079 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.COMPS.FIRST.LOCAL "27" #| 33524 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.COMPS.REST "28" #| 33108 |#,
+  ARGS.SYNSEM.LOCAL.CAT.HEAD.TAM.MOOD "29" #| 33010 |#,
+  ARGS.SYNSEM.NON-LOCAL.SLASH.LIST.FIRST.CAT.HEAD "30" #| 25870 |#,
+  ARGS.SYNSEM.LOCAL.CAT.HEAD.INV "31" #| 25009 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.COMPS.FIRST.LOCAL.CAT.MC "32" #| 21633 |#,
+  ARGS.SYNSEM.LIGHT "33" #| 18786 |#,
+  ARGS.SYNSEM.LKEYS.KEYREL "34" #| 17935 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.COMPS.FIRST.OPT "35" #| 17913 |#,
+  ARGS.SYNSEM.LOCAL.CAT.POSTHEAD "36" #| 16988 |#,
+  ARGS.SYNSEM.PUNCT.RPUNCT "37" #| 16080 |#,
+  ARGS.SYNSEM.NON-LOCAL.QUE "38" #| 15197 |#,
+  ARGS.SYNSEM.NON-LOCAL.SLASH.LIST.FIRST.CAT.HEAD.KEYS.KEY "39" #| 11901 |#,
+  ARGS.SYNSEM.LOCAL.CONT.HOOK.INDEX.SORT "40" #| 9742 |#,
+  ARGS.SYNSEM.LKEYS.KEYREL.PRED "41" #| 8621 |#,
+  ARGS.SYNSEM.LOCAL.AGR.PNG.GEN "42" #| 6062 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.SUBJ.FIRST "43" #| 5783 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.SUBJ.FIRST.OPT "44" #| 5574 |#,
+  ARGS.SYNSEM.LOCAL.CONT.RELS.LIST.REST.REST.FIRST.PRED "45" #| 5134 |#,
+  ARGS.SYNSEM.LKEYS.KEYREL.ARG0 "46" #| 4956 |#,
+  ARGS.SYNSEM.LOCAL.CONT.HOOK.INDEX.PNG.PN "47" #| 4586 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.SPR.FIRST.OPT "48" #| 4384 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.COMPS.FIRST.CLTCZD "49" #| 3876 |#,
+  ARGS.ALTS.VCALT "50" #| 3858 |#,
+  ARGS.SYNSEM.LOCAL.CONT.RELS.LIST.REST.FIRST.ARG0.SORT "51" #| 3809 |#,
+  ARGS.SYNSEM.LOCAL.CONT.RELS.LIST.REST.FIRST.ARG0.PNG.PN "52" #| 2857 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.COMPS.REST.FIRST.LOCAL "53" #| 2557 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.CLTS.REST "54" #| 2222 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.COMPS.FIRST.NON-LOCAL.SLASH "55" #| 2216 |#,
+  ARGS.ALTS "56" #| 2197 |#,
+  ARGS.SYNSEM.LOCAL.CAT.HEAD.KEYS.ALT2KEY "57" #| 2068 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.COMPS.FIRST.NON-LOCAL.SLASH.LIST "58" #| 1988 |#,
+  ARGS.SYNSEM.NON-LOCAL.SLASH.LIST.FIRST.CAT.VAL.SPR "59" #| 1953 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.SPR.FIRST.LOCAL.CAT.HEAD.KEYS.KEY "60" #| 1860 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.SUBJ.FIRST.NON-LOCAL.SLASH.LIST "61" #| 1855 |#,
+  ARGS.SYNSEM.LOCAL.STR.HEADING "62" #| 1827 |#,
+  ARGS.SYNSEM.MODIFIED "63" #| 1721 |#,
+  ARGS.SYNSEM.LOCAL.AGR.DIVISIBLE "64" #| 1208 |#,
+  ARGS.SYNSEM.LOCAL.CAT.HEAD.VOICE "65" #| 1180 |#,
+  ARGS.SYNSEM.LOCAL.CONT.HOOK.INDEX.E.TENSE "66" #| 1018 |#,
+  ARGS.SYNSEM.LOCAL.CAT.HEAD.MOD.FIRST.LOCAL.CONT.HOOK.XARG.PNG.PN "67" #| 1008 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.COMPS.FIRST.NON-LOCAL.SLASH.LAST "68" #| 978 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.SPEC.FIRST.LOCAL.CAT.HEAD.KEYS.ALTKEY "69" #| 745 |#,
+  ARGS.ALTS.CAUS "70" #| 701 |#,
+  ARGS.SYNSEM.LOCAL.CONT.RELS.LIST.REST.REST.FIRST.ARG0.PNG.GEN "71" #| 518 |#,
+  ARGS.ALTS.IMPERS "72" #| 367 |#,
+  ARGS.SYNSEM.LOCAL.CONT.HOOK.INDEX.E.MOOD "73" #| 315 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL.SPR.FIRST.LOCAL.CONT.RELS.LIST.REST "74" #| 201 |#,
+  ARGS.SYNSEM.LOCAL.CAT.HEAD.AUX "75" #| 104 |#,
+  ARGS.SYNSEM.LKEYS.ALTKEYREL.PRED "76" #| 76 |#,
+  ARGS.SYNSEM.PUNCT.LPUNCT "77" #| 29 |#,
+  ARGS.SYNSEM.LOCAL.CAT.VAL "78" #| 26 |#,
+  ARGS.SYNSEM.LOCAL.CAT.HEAD.MOD.FIRST.PUNCT.RPUNCT "79" #| 26 |# ].
+
+:end :instance.
+
+quickcheck-instance           := qc_unif_set.
 
 ;post-model-path           := "english-postagger.hmm".
 
@@ -32,6 +120,7 @@ lex-pred-path             := SYNSEM LKEYS KEYREL PRED.
 rule-rels-path            := C-CONT RELS.
 
 parsing-roots := root_vp_inf root_s root_vpnom root_np root_nbar root_pp root_ap root_rp root_c root_i.
+;parsing-roots := root_s.
 
 ;generation-roots          := root_strict root_frag.
 ;generation-roots        := root_strict.
@@ -44,6 +133,43 @@ cons-type                 := cons.
 null-type                 := null.
 diff-list-type            := diff-list.
 
+;;;Token Mapping
+
+;;;|| token-mapping || enabled (normal) or disabled (legacy; not well supported) ||
+;;;|| token-type || type of a token feature structure ||
+;;;|| lexicon-tokens-path || path to the list of tokens that license a lexeme ||
+;;;|| lexicon-tokens-last-path || path to the LAST pointer for the diff-list-like token list ||
+;;;|| token-form-path || path within a token to the surface form string ||
+;;;|| token-from-path || path within a token to the CFROM (character start position) field ||
+;;;|| token-to-path   || path within a token to the CTO (character end position) field ||
+;;;|| token-id-path   || path within a token to the ID ||
+;;;|| token-postags-path   || path within a token to the POS tag list ||
+;;;|| token-posprobs-path  || path within a token to the POS tag probability list ||
+;; token settings
+token-mapping := enabled.
+
+lexicon-tokens-path := TOKENS +LIST.
+lexicon-last-token-path := TOKENS +LAST.
+token-type      := token.
+token-form-path     := +FORM.       ; [required] string for lexical lookup
+token-id-path       := +ID.         ; [optional] list of external ids
+token-from-path     := +FROM.       ; [optional] surface start position
+token-to-path       := +TO.         ; [optional] surface end position
+token-postags-path  := +POS +TAGS.  ; [optional] list of POS tags
+token-posprobs-path := +POS +PRBS.  ; [optional] list of POS probabilities
+
+
+;;;|| lattice-mapping-input-path || path within a lattice mapping rule to the input list ||
+;;;|| lattice-mapping-output-path || path within a lattice mapping rule to the output list ||
+;;;|| lattice-mapping-context-path || path within a lattice mapping rule to the context list ||
+;;;|| lattice-mapping-position-path || path within a lattice mapping rule to the positional constraints ||
+;; lattice mapping settings
+lattice-mapping-input-path := +INPUT.
+lattice-mapping-output-path := +OUTPUT.
+lattice-mapping-context-path := +CONTEXT.
+lattice-mapping-position-path := +POSITION.
+
+
 deleted-daughters := 
   ARGS HEAD-DTR NON-HEAD-DTR.
 

debug-yy.txt

@@ -0,0 +1,3 @@
+
+
+

freeling/README

@@ -0,0 +1,32 @@
+
+  === SPPP FreeLing interface for the SRG ===
+
+  This directory contains the configuration and data files for SPPP interface
+  for the LKB Spanish  Resource Grammar, which allows it to use the low-level
+  language processors in FreeLing library.
+
+  Contents of this directory:
+
+   sppp.dat:  File with rules that control the interface behaviour, in order
+             to make it meet the needs of your LKB grammar.
+
+              You can:
+              - Specify how FreeLing output (form, lemma, PoS) is mapped 
+                to SPPP fields (stem, rule_id, form) 
+              - List forms for which all analysis are to be retained (i.e.
+                ignoring PoS tagger decisions)
+              - List forms for which FreeLing output is to be
+                changed by another user-specified list of tags.
+              - List tag combinations that are to be changed to a single tag
+
+              See the comments in sppp.dat to find out more about
+              its possiblities.
+
+   logon.cfg:  Configuration file for FreeLing. You can configure the 
+              kind of output (morphological analysys, PoS disambiguation...),
+              the linguistic resources used (e.g. form dictionary, multiword 
+              lists, enabled/disabled modules, etc.).
+               See FreeLing documentation for details on the available options.
+
+   data:  Subdirectory containing linguistic data (different than FreeLing defaults)
+          which are used in sppp.dat.