;;; -*- Mode: tdl; Coding: utf-8; -*- ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;; ;;; ;;; application- or task-specific `accommodation' rules (aka hacks :-). patch ;;; up the input token lattice as needed. in principle, such rules should go ;;; into separate modules, once we provide a mechanism to selectively activate ;;; rules or sets of rules. ;;; ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;; ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;; ;;; ;;; Experimental rules for speech input, which has not been pre-segmented to ;;; disconnect contracted forms like "I'm" or "that's" apostrophe_speech_tmr := one_two_tmt & [ +INPUT < [ +FORM ^([[:alpha:]]+)[’'](s|d|ve|ll|m|re)$, +TRAIT #trait, +PRED #pred, +CARG #carg ] >, +OUTPUT < [ +FORM "${I1:+FORM:1}", +TRAIT #trait, +PRED #pred, +CARG #carg, +TNT [ +TAGS < "NN" >, +PRBS < "1.0" > ] ], [ +FORM "’${I1:+FORM:2}", +TRAIT #trait, +PRED #pred, +CARG #carg, +TNT [ +TAGS < anti_string >, +PRBS < "1.0" > ] ] > ]. ; Optionally drop comma, since it is sometimes used just to indicate pause ; in speech transcriptions comma_pause_speech_tmr := token_mapping_rule & [ +CONTEXT < [ +FORM ^([[:alpha:]’'.-]+)(,)$, +TRAIT #trait, +PRED #pred, +CARG #carg, +TNT #tnt, +ID #id, +FROM #from, +TO #to, +CLASS #class ] >, +OUTPUT < [ +FORM "${C1:+FORM:1}", +TRAIT #trait, +PRED #pred, +CARG #carg, +TNT #tnt, +ID #id, +FROM #from, +TO #to, +CLASS #class ] >, +POSITION "C1@O1" ]. ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;; ;;; ;;; Spelling patches for training data transcripts ;;; sc_task_tmr := one_one_form_tmt & [ +INPUT < [ +FORM ^tas$] >, +OUTPUT < [ +FORM "task" ] > ]. sc_goin_tmr := one_one_form_tmt & [ +INPUT < [ +FORM ^goin$] >, +OUTPUT < [ +FORM "going" ] > ]. sc_goin_apos_tmr := one_one_form_tmt & [ +INPUT < [ +FORM ^goin'$] >, +OUTPUT < [ +FORM "going" ] > ]. sc_tryin_tmr := one_one_form_tmt & [ +INPUT < [ +FORM ^tryin$] >, +OUTPUT < [ +FORM "trying" ] > ]. sc_fer_tmr := one_one_form_tmt & [ +INPUT < [ +FORM ^fer$] >, +OUTPUT < [ +FORM "for" ] > ]. sc_thee_tmr := one_one_form_tmt & [ +INPUT < [ +FORM ^thee$] >, +OUTPUT < [ +FORM "the" ] > ]. sc_ya_tmr := one_one_form_tmt & [ +INPUT < [ +FORM ^ya$] >, +OUTPUT < [ +FORM "you" ] > ]. sc_alrright_tmr := one_one_form_tmt & [ +INPUT < [ +FORM ^alrright$] >, +OUTPUT < [ +FORM "alright" ] > ]. sc_lef_tmr := one_one_form_tmt & [ +INPUT < [ +FORM ^lef$] >, +OUTPUT < [ +FORM "left" ] > ]. sc_seve_tmr := one_one_form_tmt & [ +INPUT < [ +FORM ^seve$] >, +OUTPUT < [ +FORM "seven" ] > ].