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

IssueID #1224: replaced example for morphological lexicon

Browse Source
This commit is contained in:
Cyprian Laskowski 2020-10-16 16:00:19 +02:00
parent 8a1c1bc812
commit 68f5d8cbd5
2 changed files with 158 additions and 55 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

158
examples/morphological_lexicon/megla.xml Normal file
View File

@ -0,0 +1,158 @@
<lexicon>
<entry>
<head>
<headword>
<lemma orthography_id="343" dynamic_accentuation_id="81" pronunciation_id="32" hyphenation_id="99" tonemic_accentuation_id="777">agencija</lemma>
</headword>
<lexicalUnit sloleksId="LE_c77074df05d2719216d477bd01d418ad" sloleksKey="S_megla" type="single">
<lexeme lexical_unit_lexeme_id="83224">megla</lexeme>
</lexicalUnit>
<grammar>
<category>samostalnik</category>
<grammarFeature name="type">common</grammarFeature>
<grammarFeature name="gender">feminine</grammarFeature>
<!--grammarFeature name="pattern">Sz.1.2.o</grammarFeature-->
</grammar>
<measureList>
<measure type="frequency" source="Gigafida 2.0">285818</measure>
</measureList>
<relatedEntryList/>
</head>
<body>
<wordFormList>
<wordForm id="333330">
<msd language="sl" system="JOS">Sozdr</msd>
<msd language="en" system="UD">AUX|...</msd>
<grammarFeatureList>
<grammarFeature name="number">dual</grammarFeature>
<grammarFeature name="case">genitive</grammarFeature>
</grammarFeatureList>
<formRepresentations>
<orthographyList>
<orthography id="342" morphologyPatterns="MP.1" status="preferred">
<form>megel</form>
<measureList>
<measure type="frequency" source="Gigafida 2.0">813</measure>
<measure type="frequency" source="GOS 1.0">432</measure>
</measureList>
</orthography>
<orthography id="343" morphologyPatterns="cjvt:MP.2">
<form>megla</form>
<measureList>
<measure type="frequency" source="Gigafida 2.0">9999</measure>
<measure type="frequency" source="GOS 1.0">888</measure>
</measureList>
</orthography>
</orthographyList>
<!-- Pri accentuantion in tonemic gre v resnici za dva načina naglaševanja, ali dovoljujemo potem povsem ločena elementa "tonemic" in "accentuation"? Če hočemo, da je vse pod "accentuation" in se razlikujeta po "type", potem je problem v glavi, kjer pri lemi navajamo npr. "accentuation_id", ki bi se potem moral pojaviti dvakrat? -->
<!-- Pri nekaterih vzorcih se stvari zelo ponavljajo; pri ZRC-ju npr. ločujejo meglA in mEgla -->
<accentuationList type="dynamic">
<accentuation id="81" orthography_id="342" stressPatterns="cjvt:AP.1|zrc:S202b" status="preferred">
<form>mègel</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
<accentuation id="82" orthography_id="343" stressPatterns="AP.1">
<form>meglá</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
<accentuation id="83" orthography_id="342" stressPatterns="AP.2" status="preferred">
<form>mègel</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
<accentuation id="84" orthography_id="343" stressPatterns="AP.2">
<form>meglá</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
</accentuationList>
<accentuationList type="tonemic">
<!-- tonemicPatterns je pri ZRC-ju v resnici združen z oblikoslovnim in naglasnim vzorcem, kar je mogoče problematično, saj bi ga v Sloleksu potem morali navesti tako pod orthography kot pod accentuation/tonemic. -->
<accentuation id="85" orthography_id="342" stressPatterns="S202b|S202i" status="preferred">
<form>mȅgel</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
<accentuation id="86" orthography_id="343" stressPatterns="S202b">
<form>meglā</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
<accentuation id="87" orthography_id="342" stressPatterns="S202i">
<form>mȅgel</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
<accentuation id="88" orthography_id="343" stressPatterns="S202i">
<form>meglā</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
</accentuationList>
<pronunciationList>
<pronunciation id="32" dynamic_accentuation_id="81" tonemic_accentuation_id="85" status="preferred">
<form script="IPA">mɛˈɡel</form>
<form script="SAMPA">mE"ɡel</form>
<measureList><!-- Ali obstaja več measureListov, po eden za vsak form? Ali pa povezujemo vsak measure z ustreznim form? -->
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
<pronunciation id="33" dynamic_accentuation_id="82" tonemic_accentuation_id="86">
<form script="IPA">mɛˈɡla</form>
<form script="SAMPA">mE"ɡla</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
<pronunciation id="34" dynamic_accentuation_id="82" norm="non-standard">
<form script="IPA">mɛˈγla</form>
<form script="SAMPA">mE"γla</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
<pronunciation id="35" dynamic_accentuation_id="81" norm="non-standard">
<form script="IPA">mɛˈγel</form>
<form script="SAMPA">mE"γel</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
</pronunciationList>
<hyphenationList>
<hyphenation id="7" orthography_id="342">
<form>me|gel</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</hyphenation>
<hyphenation id="8" orthography_id="81">
<form>mè|gel</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</hyphenation>
<hyphenation id="8" orthography_id="82">
<form>me|glá</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</hyphenation>
</hyphenationList>
</formRepresentations>
</wordForm>
</wordFormList>
</body>
</entry>
</lexicon>

55
examples/morphological_lexicon/sloleks_example.xml
View File

@ -1,55 +0,0 @@
<lexicon>
<entry>
<head>
<headword>
<lemma>klop</lemma>
</headword>
<lexicalUnit id="123456" type="single">
<lexeme lexical_unit_lexeme_id="654321">klop</lexeme>
</lexicalUnit>
<grammar>
<category>samostalnik</category>
<grammarFeature name="type">common</grammarFeature>
<grammarFeature name="gender">feminine</grammarFeature>
<grammarFeature name="pattern">Sz.1.2.o</grammarFeature>
</grammar>
<measureList>
<measure type="frequency" source="Gigafida 2.0">999999</measure>
</measureList>
</head>
<body>
<wordFormList>
<wordForm id="333333">
<msd language="sl" system="JOS">Sozim</msd>
<grammarFeatureList>
<grammarFeature name="case">nominative</grammarFeature>
<grammarFeature name="number">plural</grammarFeature>
</grammarFeatureList>
<formRepresentationList>
<formRepresentation id="4444444">
<measureList>
<measure type="frequency" source="Gigafida 2.0">222222</measure>
</measureList>
<form>klopi</form>
</formRepresentation>
</formRepresentationList>
</wordForm>
<wordForm id="333334">
<msd language="sl" system="JOS">Sozdm</msd>
<grammarFeatureList>
<grammarFeature name="case">dative</grammarFeature>
<grammarFeature name="number">plural</grammarFeature>
</grammarFeatureList>
<formRepresentationList>
<formRepresentation id="4444445">
<measureList>
<measure type="frequency" source="Gigafida 2.0">11111</measure>
</measureList>
<form>klopem</form>
</formRepresentation>
</formRepresentationList>
</wordForm>
</wordFormList>
</body>
</entry>
</lexicon>