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

Merge branch 'master' into dev

Browse Source
This commit is contained in:
Cyprian Laskowski 2020-02-27 10:08:16 +01:00
commit 8639397050
1 changed files with 171 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

171
examples/valency_lexicon/valency_manual_example_simplified.xml Normal file
View File

@ -0,0 +1,171 @@
<dictionary xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:noNamespaceSchemaLocation="valency_lexicon.xsd">
<entry>
<head>
<headword>
<lemma>aktivirati</lemma>
</headword>
<lexicalUnit id="317" type="single">
<lexeme lexical_unit_lexeme_id="317">aktivirati</lexeme>
</lexicalUnit>
<grammar>
<!-- tekst in vrednosti atributov v slovenscini, rabimo pa moznost switcha v anglescini na nek nacin -->
<category>glagol</category>
<grammarFeature name="vid">dvovidski</grammarFeature>
<!-- iz Sloleksa -->
</grammar>
<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>
<!-- iz Gigafide -->
<measure type="frequency" source="ssj500k 2.2">5</measure>
<!-- iz ssj500k -->
</measureList>
</head>
<body>
<statisticsContainerList>
<statisticsContainer>
<semanticRole>PAT</semanticRole>
<measureList>
<measure type="valency_pattern_ratio">0.37</measure>
<!-- odstotek vzorcev, v katerih se pojavlja PAT -->
<measure type="valency_sentence_ratio">0.19</measure>
<!-- odstotek stavkov (v kateremkoli vzorcu), v katerih se pojavlja PAT -->
</measureList>
</statisticsContainer>
<statisticsContainer>
<semanticRole>AIM</semanticRole>
<measureList>
<measure type="valency_pattern_ratio">0.81</measure>
<!-- odstotek vzorcev, v katerih se pojavlja AIM -->
<measure type="valency_sentence_ratio">0.1</measure>
<!-- odstotek stavkov (v kateremkoli vzorcu), v katerih se pojavlja AIM -->
</measureList>
</statisticsContainer>
</statisticsContainerList>
<senseList>
<sense id="317">
<definitionList/>
<valencyPatternList>
<valencyPattern id="2">
<measureList>
<measure type="frequency_all" source="Gigaida 2.0">7</measure>
<!-- število stavkov s tem vzorcem -->
<measure type="frequency_all" source="ssj500k 2.2">1</measure>
</measureList>
<semanticRoleContainerList>
<semanticRoleContainer>
<semanticRole>PAT</semanticRole>
<syntacticStructureList system="JOS">
<syntacticStructure id="8"/>
<!-- iz datoteke: Kolokacije_strukture_JOS-32-representation.xml -->
</syntacticStructureList>
</semanticRoleContainer>
<semanticRoleContainer>
<semanticRole>AIM</semanticRole>
<syntacticStructureList system="JOS">
<syntacticStructure id="36">
<component num="3">
<lexeme sloleks="">za</lexeme>
</component>
</syntacticStructure>
</syntacticStructureList>
</semanticRoleContainer>
</semanticRoleContainerList>
<patternRepresentation>aktivirati KOGA/KAJ S KAKŠNIM NAMENOM</patternRepresentation>
<exampleContainerList>
<exampleContainer>
<corpusExample modified="false">
Glede vabe ušata res ni izbirčna
<tree role="AIM">
<comp structure_id="36" num="3">za</comp>
uspešen
<comp structure_id="36" num="4">ribolov</comp>
</tree>
pa
<tree role="PAT">
<comp structure_id="8" num="4">jo</comp>
</tree>
moramo
<comp role="headword">aktivirati</comp>,
jih obnoreti, preslepiti.
</corpusExample>
</exampleContainer>
</exampleContainerList>
</valencyPattern>
<valencyPattern id="3">
<measureList>
<measure type="frequency_all" source="GF2.0">20</measure>
<!-- število stavkov s tem vzorcem -->
<measure type="frequency_all" source="ssj500k">0</measure>
</measureList>
<semanticRoleContainerList>
<semanticRoleContainer>
<semanticRole>ACT</semanticRole>
<syntacticStructureList system="JOS">
<syntacticStructure id="9"/>
<!-- iz datoteke: Kolokacije_strukture_JOS-32-representation.xml -->
</syntacticStructureList>
</semanticRoleContainer>
<semanticRoleContainer>
<semanticRole>PAT</semanticRole>
<syntacticStructureList system="JOS">
<syntacticStructure id="8"/>
<syntacticStructure id="33">
<component num="2">
<lexeme sloleks="">z/s</lexeme>
</component>
</syntacticStructure>
</syntacticStructureList>
</semanticRoleContainer>
<semanticRoleContainer>
<semanticRole>MANN</semanticRole>
<syntacticStructureList system="JOS">
<syntacticStructure id="19"/>
<syntacticStructure id="36">
<component num="3">
<lexeme sloleks="">na</lexeme>
</component>
<component num="3">
<lexeme sloleks="">pred</lexeme>
</component>
</syntacticStructure>
<syntacticStructure id="33">
<component num="2">
<lexeme sloleks="">z/s</lexeme>
</component>
</syntacticStructure>
<syntacticStructure id="34">
<component num="3">
<lexeme sloleks="">preko</lexeme>
</component>
</syntacticStructure>
</syntacticStructureList>
</semanticRoleContainer>
</semanticRoleContainerList>
<patternRepresentation>KDO/KAJ aktivira KOGA/KAJ KAKO</patternRepresentation>
<exampleContainerList>
<exampleContainer>
<corpusExample modified="false">
<tree role="ACT">
<comp structure_id="9" num="1">Poljubljanje</comp>
</tree>
<tree role="MANN">
<comp structure_id="19" num="1">hitro</comp>
</tree>
<comp role="headword">aktivira</comp>
<tree role="PAT">
<comp structure_id="8" num="4">hormon</comp>
sreče
</tree>
in krepi imunski sistem.
</corpusExample>
</exampleContainer>
</exampleContainerList>
</valencyPattern>
</valencyPatternList>
</sense>
</senseList>
</body>
</entry>
</dictionary>