generic/xml_schemas
16
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

IssueID #959: tweaked valency schema details

Browse Source
This commit is contained in:
Cyprian Laskowski 2020-02-25 17:02:59 +01:00
parent 1eb865b088
commit 9f1b0580f7
2 changed files with 28 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
examples/valency_lexicon/valency_manual_example.xml
View File

@ -9,21 +9,23 @@
<lexeme lexical_unit_lexeme_id="317">aktivirati</lexeme> <lexeme lexical_unit_lexeme_id="317">aktivirati</lexeme>
</lexicalUnit> </lexicalUnit>
<grammar> <grammar>
<!-- tekst in vrednosti atributov v slovenscini, rabimo pa moznost switcha v anglescini na nek nacin -->
<category>glagol</category> <category>glagol</category>
<grammarFeature name="Aspect">biaspectual</grammarFeature> <grammarFeature name="vid">dvovidski</grammarFeature>
<!-- iz Sloleksa --> <!-- iz Sloleksa -->
</grammar> </grammar>
<measureList> <measureList>
<!-- vrednosti za @source naceloma se morajo ujemati z dogovori s Tomazom o imenih korpusov itd -->
<measure type="frequency" source="Gigafida 2.0">11410</measure> <measure type="frequency" source="Gigafida 2.0">11410</measure>
<!-- iz Gigafide --> <!-- iz Gigafide -->
<measure type="frequency" source="ssj500k 2.2">5</measure> <measure type="frequency" source="ssj500k 2.2">5</measure>
<!-- iz ssj500k --> <!-- iz ssj500k -->
</measureList> </measureList>
<labelList> <labelList>
<label type="Levin_class" feature_id="55">"begin" verbs</label> <label type="Levin_class" featureId="55.1">"begin" verbs</label>
<!-- iz Levin classes list http://www-personal.umich.edu/~jlawler/levin.verbs --> <!-- iz Levin classes list http://www-personal.umich.edu/~jlawler/levin.verbs -->
<label type="Žele_class" feature_id="56">glagol ravnanja</label> <label type="Žele_class" featureId="56">glagol ravnanja</label>
<!-- Žele: vezljivostni slovar --> <!-- Žele: vezljivostni slovar https://fran.si/209/vezljivostni-slovar/4410086/aktivirati?FilteredDictionaryIds=209&View=1&Query=aktivirati -->
</labelList> </labelList>
</head> </head>
<body> <body>
@ -31,18 +33,18 @@
<statisticsContainer> <statisticsContainer>
<semanticRole>PAT</semanticRole> <semanticRole>PAT</semanticRole>
<measureList> <measureList>
<measure type="valency_pattern_ratio" ratio_base="148">50</measure> <measure type="valency_pattern_ratio">0.37</measure>
<!-- odstotek vzorcev, v katerih se pojavlja PAT --> <!-- odstotek vzorcev, v katerih se pojavlja PAT -->
<measure type="valency_sentence_ratio">100</measure> <measure type="valency_sentence_ratio">0.19</measure>
<!-- odstotek stavkov (v kateremkoli vzorcu), v katerih se pojavlja PAT --> <!-- odstotek stavkov (v kateremkoli vzorcu), v katerih se pojavlja PAT -->
</measureList> </measureList>
</statisticsContainer> </statisticsContainer>
<statisticsContainer> <statisticsContainer>
<semanticRole>AIM</semanticRole> <semanticRole>AIM</semanticRole>
<measureList> <measureList>
<measure type="valency_pattern_ratio" ratio_base="1">1</measure> <measure type="valency_pattern_ratio">0.81</measure>
<!-- odstotek vzorcev, v katerih se pojavlja AIM --> <!-- odstotek vzorcev, v katerih se pojavlja AIM -->
<measure type="valency_sentence_ratio">100</measure> <measure type="valency_sentence_ratio">0.1</measure>
<!-- odstotek stavkov (v kateremkoli vzorcu), v katerih se pojavlja AIM --> <!-- odstotek stavkov (v kateremkoli vzorcu), v katerih se pojavlja AIM -->
</measureList> </measureList>
</statisticsContainer> </statisticsContainer>
@ -69,7 +71,7 @@
<semanticRole>AIM</semanticRole> <semanticRole>AIM</semanticRole>
<syntacticStructureList> <syntacticStructureList>
<syntacticStructure id="36"> <syntacticStructure id="36">
<comp structure_component_index="3">za</comp> <comp num="3">za</comp>
</syntacticStructure> </syntacticStructure>
</syntacticStructureList> </syntacticStructureList>
</semanticRoleContainer> </semanticRoleContainer>
@ -80,13 +82,12 @@
<corpusExample corpus_id="1" modified="false"> <corpusExample corpus_id="1" modified="false">
Glede vabe ušata res ni izbirčna Glede vabe ušata res ni izbirčna
<tree role="AIM"> <tree role="AIM">
<comp syntactic_structure_id="36" structure_component_index="3">za</comp> <comp structure_id="36" num="3">za</comp>
uspešen <comp structure_id="36" num="4">ribolov</comp>
<comp syntactic_structure_id="36" structure_component_index="4">ribolov</comp>
</tree> </tree>
pa pa
<tree role="PAT"> <tree role="PAT">
<comp syntactic_structure_id="8" structure_component_index="4">jo</comp> <comp structure_id="8" num="4">jo</comp>
</tree> </tree>
moramo moramo
<comp role="headword">aktivirati</comp>, <comp role="headword">aktivirati</comp>,
@ -97,13 +98,13 @@
<corpusExample modified="false"> <corpusExample modified="false">
Glede vabe ušata res ni izbirčna Glede vabe ušata res ni izbirčna
<tree role="AIM"> <tree role="AIM">
<comp syntactic_structure_id="36" structure_component_index="3">za</comp> <comp structure_id="36" num="3">za</comp>
uspešen uspešen
<comp syntactic_structure_id="36" structure_component_index="4">ribolov</comp> <comp structure_id="36" num="4">ribolov</comp>
</tree> </tree>
pa pa
<tree role="PAT"> <tree role="PAT">
<comp syntactic_structure_id="8" structure_component_index="4">jo</comp> <comp structure_id="8" num="4">jo</comp>
</tree> </tree>
moramo moramo
<comp role="headword">aktivirati</comp>, <comp role="headword">aktivirati</comp>,
@ -131,7 +132,7 @@
<syntacticStructureList> <syntacticStructureList>
<syntacticStructure id="8"/> <syntacticStructure id="8"/>
<syntacticStructure id="33"> <syntacticStructure id="33">
<comp structure_component_index="2">z/s</comp> <comp num="2">z/s</comp>
</syntacticStructure> </syntacticStructure>
</syntacticStructureList> </syntacticStructureList>
</semanticRoleContainer> </semanticRoleContainer>
@ -140,14 +141,14 @@
<syntacticStructureList system="JOS"> <syntacticStructureList system="JOS">
<syntacticStructure id="19"/> <syntacticStructure id="19"/>
<syntacticStructure id="36"> <syntacticStructure id="36">
<comp structure_component_index="3">na</comp> <comp num="3">na</comp>
<comp structure_component_index="3">pred</comp> <comp num="3">pred</comp>
</syntacticStructure> </syntacticStructure>
<syntacticStructure id="33"> <syntacticStructure id="33">
<comp structure_component_index="2">z/s</comp> <comp num="2">z/s</comp>
</syntacticStructure> </syntacticStructure>
<syntacticStructure id="34"> <syntacticStructure id="34">
<comp structure_component_index="3">preko</comp> <comp num="3">preko</comp>
</syntacticStructure> </syntacticStructure>
</syntacticStructureList> </syntacticStructureList>
</semanticRoleContainer> </semanticRoleContainer>
@ -157,14 +158,14 @@
<exampleContainer> <exampleContainer>
<corpusExample modified="false"> <corpusExample modified="false">
<tree role="ACT"> <tree role="ACT">
<comp syntactic_structure_id="9" structure_component_index="1">Poljubljanje</comp> <comp structure_id="9" num="1">Poljubljanje</comp>
</tree> </tree>
<tree role="MANN"> <tree role="MANN">
<comp syntactic_structure_id="19" structure_component_index="1">hitro</comp> <comp structure_id="19" num="1">hitro</comp>
</tree> </tree>
<comp role="headword">aktivira</comp> <comp role="headword">aktivira</comp>
<tree role="PAT"> <tree role="PAT">
<comp syntactic_structure_id="8" structure_component_index="4">hormon</comp> <comp structure_id="8" num="4">hormon</comp>
sreče sreče
</tree> </tree>
in krepi imunski sistem. in krepi imunski sistem.

5
resources/schema/inventory.xsd
View File

@ -146,6 +146,7 @@
<xsd:simpleContent> <xsd:simpleContent>
<xsd:extension base="xsd:string"> <xsd:extension base="xsd:string">
<xsd:attribute name="feature_id" type="xsd:int"/> <xsd:attribute name="feature_id" type="xsd:int"/>
<xsd:attribute name="featureId" type="xsd:string"/>
<xsd:attribute name="type" type="xsd:string"/> <xsd:attribute name="type" type="xsd:string"/>
</xsd:extension> </xsd:extension>
</xsd:simpleContent> </xsd:simpleContent>
@ -186,8 +187,8 @@
<xsd:simpleContent> <xsd:simpleContent>
<xsd:extension base="xsd:string"> <xsd:extension base="xsd:string">
<xsd:attribute name="lexical_unit_lexeme_id" type="xsd:int"/> <xsd:attribute name="lexical_unit_lexeme_id" type="xsd:int"/>
<xsd:attribute name="syntactic_structure_id" type="xsd:int"/> <xsd:attribute name="structure_id" type="xsd:int"/>
<xsd:attribute name="structure_component_index" type="xsd:int"/> <xsd:attribute name="num" type="xsd:int"/>
<xsd:attribute name="lexeme_id" type="xsd:int"/> <xsd:attribute name="lexeme_id" type="xsd:int"/>
<xsd:attribute name="role"> <xsd:attribute name="role">
<xsd:simpleType> <xsd:simpleType>