;;; -*- Mode: TDL; Coding: utf-8 -*- ;;;; cheap.settings ;;;; settings for CHEAP preprocessor := "preprocessor.fsr". pn-label-type := label-sign. pn-prefix-path := META-PREFIX. pn-suffix-path := META-SUFFIX. pn-recursive-path := SYNSEM.NONLOC.SLASH. pn-local-path := SYNSEM.LOC. ersatz-carg-path := "SYNSEM.LKEYS.KEYTAG". ;; definition of names of types with a special meaning to PET special-name-top := "*top*". special-name-symbol := "symbol". special-name-string := "string". special-name-cons := "*cons*". special-name-list := "*list*". special-name-nil := "*null*". special-name-difflist := "*diff-list*". ;; same for attributes special-name-attr-first := "FIRST". special-name-attr-rest := "REST". special-name-attr-list := "LIST". special-name-attr-last := "LAST". special-name-attr-args := "ARGS". ;; name of type to get info about grammar into (if at all) grammar-info := grammar_info. ;; MRS postload-lisp-files := "mrsglobals.lsp". ;; status values that mark rules rule-status-values := rule. lexrule-status-values := lex-rule. ;; status values that mark infl rules ;infl-rule-status-values := infl-rule. ;; status values that mark lexicon entries lexentry-status-values := lex-entry. ;; path to the list of arguments in a rule rule-args-path := ARGS. ;; path to marker for key argument of a rule keyarg-marker-path := KEY-ARG. ;; path to marker for head dtr of a rule head-dtr-path := HEAD-DTR. ;; path to orthography orth-path := "MORPH.LIST.FIRST.STEM". ;; type to mark boolean value `true' true-type := +. ;; type of a valid parse start-symbols := $utterance-v-scnd $utterance-non-v $utterance-turn-seq $utterance-coord $utterance-int-clause. ; $mal-utterance-v-scnd $mal-utterance-v-scnd-nopunct $mal-utterance-non-v $mal-utterance-turn-seq $mal-utterance-coord. ; $utterance-v-scnd-ignp $utterance-turn-seq-ignp $utterance-coord-ignp . ;; names of attributes not to pass from daughter to mother in parsing deleted-daughters := ARGS HEAD-DTR NON-HEAD-DTR. ;; prefix of list-valued path where to unify the affix ;affixation-path := "ARGS.FIRST". ;; path into the MRS semantics ;mrs-path := "SYNSEM.LOC.CONT". include "mrs". ; ;; (BK 2004-04-06) path into the MRSs CFROM, CTO, and CARG ;; ;mrs-cfrom-path := "SYNSEM.LOC.CONT.RELS.LIST.CFROM". ;mrs-cto-path := "SYNSEM.LOC.CONT.RELS.LIST.CTO". ;mrs-carg-path := "SYNSEM.LOC.CONT.KEY.CARG". ;; ;; path to LABEL for relation-to-word mapping, absolute and within a relation ;; label-path := "SYNSEM.LOC.CONT.KEY.WLINK". label-path-tail := "WLINK". encoding := utf-8. ;; list of characters for the tokenizer to ignore, default is ;; "\t?!.:;,()-+*$\n" ;; removed `-' because of `I-C-E' and `Berlin-Zehlendorf' punctuation-characters := "“”‘‘". ;; allow creation of lexical entries to fail lex-entries-can-fail. ;; chart manipulation for separable prefixes ;; contains a list of pairs of paths lex-exhaustive. unidirectional-chart-dependencies. chart-dependencies := "SYNSEM.LOC.CAT.HEAD.SP-FORM" "SYNSEM.LOC.CAT.VCOMP.FIRST.LOC.CAT.HEAD.SP-FORM" "SYNSEM.LOC.CAT.VCOMP.FIRST.LOC.CAT.HEAD.SP-FORM" "SYNSEM.LOC.CAT.HEAD.SP-FORM" "SYNSEM.LOC.CAT.HEAD._VFORM" "SYNSEM.LOC.CAT.VCOMP.FIRST.LOC.CAT.HEAD._VFORM" "SYNSEM.LOC.CAT.VCOMP.FIRST.LOC.CAT.HEAD._VFORM" "SYNSEM.LOC.CAT.HEAD._VFORM" "SYNSEM.LOC.CAT.HEAD.__VC" "SYNSEM.LOC.CAT.VCOMP.FIRST.LOC.CAT.HEAD.__VC" "SYNSEM.LOC.CAT.SUBCAT.LIST.FIRST.LOC.CAT.HEAD.PFORM" "SYNSEM.LOC.CAT.HEAD.PFORM" "SYNSEM.LOC.COORD._DEPCOORDFORM" "SYNSEM.LOC.COORD._MYCOORDFORM" . posmapping := NN $generic_count_noun NN $generic_mass_noun NE $generic_name ADJA $generic_adja ADJD $generic_adjd ADJD $generic_adverb ADV $generic_adverb CARD $generic_number CARD $generic_ordinal CARD $generic_year VVFIN $generic_itr_fin_verb VVFIN $generic_tr_fin_verb VVFIN $generic_scomp_fin_verb VVIMP $generic_itr_verb VVIMP $generic_tr_verb VVIMP $generic_scomp_verb VVINF $generic_itr_inf_verb VVINF $generic_tr_inf_verb VVINF $generic_scomp_inf_verb VVPP $generic_itr_pp_verb VVPP $generic_tr_pp_verb VVPP $generic_scomp_pp_verb VVINF $generic_itr_part_inf_verb VVINF $generic_tr_part_inf_verb VVINF $generic_scomp_part_inf_verb VVIZU $generic_itr_part_izu_verb VVIZU $generic_tr_part_izu_verb VVIZU $generic_scomp_part_izu_verb . ;orthographemics-cohesive-chains := true. ;orthographemics-maximum-chain-depth := 5. ;orthographemics-duplicate-filter := true. ;orthographemics-minimum-stem-length := 1. ;positions-are-counts. ;;; ;;; following are a number of settings for the new (as of late 2008) token ;;; mapping and lexical filtering support in PET. ;;; ;; ;; first, the general format of chart mapping rules, much like MRS transfer. ;; chart-mapping-context-path := "+CONTEXT". chart-mapping-input-path := "+INPUT". chart-mapping-output-path := "+OUTPUT". chart-mapping-position-path := "+POSITION". ;; ;; in lexical instatiation, the list of tokens activating a lexical entry (be ;; it native or generic) are unified into the lexical entry under this path. ;; lexicon-tokens-path := "TOKENS.+LIST". lexicon-last-token-path := "TOKENS.+LAST". ;; ;; furthermore, for the various input formats, we need to declare how parts of ;; input descriptions correspond to the grammar-internal feature geometry; in ;; the YY input format, for example, token feature structures (aka input items ;; PET-internally) are created from various parts of the token description. ;; 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 := "+TNT.+TAGS". ; [optional] list of POS tags token-posprobs-path := "+TNT.+PRBS". ; [optional] list of POS probabilities ;; ;; finally, declare TDL status values for the various new entity types ;; generic-lexentry-status-values := generic-lex-entry. token-mapping-rule-status-values := token-mapping-rule. lexical-filtering-rule-status-values := lexical-filtering-rule.