lima-common-fre.xml

<?xml version='1.0' encoding='UTF-8'?>
<modulesConfig>
  <module name="MediaData">
    <group name="Class">
      <!-- The class to instantiate to read the content of this file -->
      <param key="class" value="LanguageData"/>
    </group>
  </module>
  <module name="LinguisticData">
    <!--All parameters related to port-of-speech tags      -->
    <group name="Categories">
        <!-- micro categories marking sentence breaks       -->
        <list name="sentenceBreakMicros">
          <item value="PONCTU_FORTE"/>
        </list>
        <!-- File containing the definition of all linguistic codes for this language        -->
      <param key = "PropertyCodeFile" value = "LinguisticProcessings/fre/code-fre.xml" />
      <!-- tokens with these macro categories will be considered as empty words-->
      <list name="emptyMacro">
        <item value="NONE_1" />
        <item value="DET" />
        <item value="PRON" />
        <!--item value="ADV" /-->
        <item value="PREP" />
        <item value="CONJ" />
        <item value="PONCTU" />
        <item value="INTERJ" />
        <!--item value="DIVERS" /-->
      </list>
      <!-- tokens with these micro categories will be considered as empty words-->
      <list name="emptyMicro">
        <item value="ADV" />
        <item value="ADVWH" />
        <item value="CC" />
        <item value="CL"/>
        <item value="CLO"/>
        <item value="CLR"/>
        <item value="CLS"/>
        <item value="CS" />
        <item value="DET"/>
        <item value="I"/>
        <item value="P"/>
        <item value="P+D"/>
        <item value="PONCT" />
        <item value="PONCTU_FORTE" />
        <item value="PRO"/>
        <item value="PROREL"/>
        <item value="PROWH"/>
      </list>
      <!-- tokens with these micro categories will be considered as conjugated verbs during syntactic analysis (i.e. not infinitive) -->
      <list name="conjugatedVerbs" >
        <item value="V" />
        <item value="VIMP" />
        <item value="VPP" />
        <item value="VPR" />
        <item value="VS" />
      </list>
      <!-- tokens with these micro categories will be considered as able to introduce proposition during syntactic analysis -->
      <list name="propositionIntroductors" >
        <item value="CC" />
        <item value="CS" />
        <item value="PRO" />
        <item value="CL" />
        <item value="CLO" />
        <item value="CLS" />
      </list>
    </group>
    <!-- The list of all syntactic relations for this language. Allows to associate them with a numeric id -->
    <group name="SyntacticRelations">
      <list name="relationList">
        <item value="DETSUB"/>
        <item value="ADJPRENSUB"/>
        <item value="COMPADJ"/>
        <item value="COMPADV"/>
        <item value="ADVADJ"/>
        <item value="ADVADV"/>
        <item value="SUBADJPOST"/>
        <item value="COMPDUNOM"/>
        <item value="COMPDUNOM2"/>
        <item value="SUBSUBJUX"/>
        <item value="TEMPCOMP"/>
        <item value="COMP_N-N"/>
        <item value="COMP_AJ-N"/>
        <item value="COMP_V-N"/>
        <item value="COMP_AV-N"/>
        <item value="COMP_N-ADJ"/>
        <item value="COMP_AJ-ADJ"/>
        <item value="COMP_V-ADJ"/>
        <item value="COMP_AV-ADJ"/>
        <item value="COMP_N-V"/>
        <item value="COMP_AJ-V"/>
        <item value="COMP_V-V"/>
        <item value="COMP_AV-V"/>
        <item value="ADJSUB"/>
        <item value="SUBADJPOST2"/>
        <item value="DETADJ"/>
        <item value="DetAdv"/><!-- for things like "les plus utilisés"-->
        <item value="PREPSUB"/>
        <item value="ADJPRENSUB_INC"/>
        <item value="DETSUB_INC"/>
        <item value="COMPADJ_INC"/>
        <item value="COMPADV_INC"/>
        <item value="SUBADJPOST_INC"/>
        <item value="COMPDUNOM_INC"/>
        <item value="SUBSUBJUX_INC"/>
        <item value="DetPron"/>
        <item value="DetIntSub"/>
        <item value="PrepDetInt"/>
        <item value="SujInv"/>
        <item value="Neg"/>
        <item value="NePas"/>
        <item value="CodPrev"/>
        <item value="DetAdj"/>
        <item value="SUJ_V"/>
        <item value="COD_V"/>
        <item value="CPL_V"/>
        <item value="MOD_V"/>
        <item value="ADVADV2"/>
        <item value="PrepInf"/>
        <item value="PronSujVerbe"/>
        <item value="COMPL"/>
        <item value="MOD_N"/>
        <item value="MOD_A"/>
        <item value="ATB_S"/>
        <item value="ATB_O"/>
        <item value="COORD1"/>
        <item value="COORD2"/>
        <item value="PrepPronRelCa"/>
        <item value="PronReflVerbe"/>
        <item value="AdvVerbe"/>
        <item value="CoiPrev"/>
        <item value="PrepPron"/>
        <item value="PrepPronRel"/>
        <item value="CodAnaph"/>
        <item value="DETSUB2"/>
        <item value="SUBADJPOST2"/>
        <item value="PrepPronCliv"/>
        <item value="PrepAdv"/>
        <item value="PrepPartPres"/>
        <item value="AdvSub"/>
        <item value="AdvSub2"/>
        <item value="Neg2"/>
        <item value="NePas2"/>
        <item value="AdvSub2"/>
        <item value="COMPADV2"/>
        <item value="TIl"/>
        <item value="APPOS"/>
        <item value="JUXT"/>
        <item value="DetSubNum"/>
        <item value="CPLV_V"/>
        <item value="CC_TEMPS"/>
        <item value="CC_LIEU"/>
        <item value="CC_BUT"/>
        <item value="CC_MOYEN"/>
        <item value="CC_MANIERE"/>
        <item value="Pleon"/>
        <item value="Prefixe"/>
        <item value="Dummy"/>
        <item value="SUJ_V_REL"/>
        <!--for simplication rules-->
        <item value="SubSent"/>
        <item value="SubordRel"/>
        <item value="Parent"/>
        <item value="Quotes"/>
        <item value="VirguleSeule"/>
        <item value="Appos"/>
        <item value="AdvSeul"/>
        <item value="AdvInit"/>
        <item value="CompAdv"/>
        <item value="Adverbe"/>
        <item value="ConjInfSecond"/>
        <item value="CCInit"/>
        <item value="Infinitive"/>
        <item value="SUBSUBJUX"/>
        <item value="CompDuNom1"/>
        <item value="CompDuNom2"/>
        <item value="CompAdj1"/>
        <item value="CompAdj2"/>
        <item value="SubordParticipiale"/>
        <item value="ElemListe"/>
        <item value="ConjSecond"/>
        <item value="InciseNom"/>
        <item value="CompCirc"/>
        <item value="SubordInit"/>
        <item value="ConjNominale"/>
        <item value="PonctuationBounds"/>
        <item value="Interjonction"/>
        <item value="AdjNom"/>
        <item value="DetAdv"/><!-- for things like "les plus utilisés"-->
        <item value="PrepDetNum"/><!-- for things like "une femme active sur cinq est..."-->
        <item value="IncInc"/><!-- to link unknown works, typically from a foreign language-->
        <!-- Start to integrate Universal Dependencies -->
        <item value="aux"/>
        <item value="auxpass"/>
        <item value="det"/>
        <item value="acl"/>
      </list>
    </group>
    <group name="SyntacticAnalysis">
      <!-- File giving the micro category of a coumpound tense verb in function of the auxiliary and the participle       -->
      <param key="CompoundTensesDefFile" value="SyntacticAnalysis/compoundTenses-fre.bin"/>
      <!-- List of micro categories followed for building a LIMA nominal chain (a kind of maximal chunk)       -->
      <list name="NominalHomoSyntagmaticRelations">
        <item value="DETSUB"/>
        <item value="DetPron"/>
        <item value="DetAdj"/>
        <item value="ADJPRENSUB"/>
        <item value="COMPADJ"/>
        <item value="COMPADV"/>
        <item value="ADVADJ"/>
        <item value="ADVADV"/>
        <item value="SUBADJPOST"/>
        <item value="COMPDUNOM"/>
        <item value="SUBSUBJUX"/>
        <item value="DetIntSub"/>
        <item value="DetSubNum"/>
        <item value="PrepDetInt"/>
        <item value="PREPSUB"/>
        <item value="PrepPronRelCa"/>
        <item value="PrepPron"/>
        <item value="PrepPronRel"/>
        <item value="PrepAdv"/>
        <item value="AdvSub"/>
        <item value="Prefixe"/>
      </list>
      <!-- List of micro categories followed for building a LIMA verbal chain (a kind of maximal chunk)       -->
      <list name="VerbalHomoSyntagmaticRelations">
        <item value="SujInv"/>
        <item value="CodPrev"/>
        <item value="CoiPrev"/>
        <item value="Neg"/>
        <item value="NePas"/>
        <item value="NePas2"/>
        <item value="PrepInf"/>
        <item value="PrepPartPres"/>
        <item value="ADVADV"/>
        <item value="PronSujVerbe"/>
        <item value="PronReflVerbe"/>
        <item value="AdvVerbe"/>
        <item value="TEMPCOMP"/>
        <item value="CodAnaph"/>
        <item value="TIl"/>
      </list>
      <!--The list of micro categories defining tokens that can be head of noun phrases. Used during coreference solving -->
      <list name="NounPhraseHeadCategs">
        <item value="NC"/>
        <item value="NPP"/>
        <item value="CL"/>
        <item value="CLO"/>
        <item value="CLS"/>
        <item value="CLR"/>
        <item value="PRO"/>
        <item value="PROREL"/>
        <item value="PROWH"/>
      </list>
      <!--The list of micro categories defining tokens that introduce a definite noun. Used during coreference solving -->
      <list name="DefiniteCategs">
        <item value="DET"/>
      </list>
    </group>
  </module>
</modulesConfig>