Skip to content
Snippets Groups Projects
Commit e6e0232a authored by Adam Radziszewski's avatar Adam Radziszewski
Browse files

some real-life tests from M.M.

parent 39360618
Branches
No related merge requests found
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE cesAna SYSTEM "xcesAnaIPI.dtd">
<cesAna xmlns:xlink="http://www.w3.org/1999/xlink" version="1.0" type="lex disamb">
<chunkList>
<chunk>
<sentence>
<tok>
<orth>To</orth>
<lex><base>ten</base><ctag>adj:sg:nom:n:pos</ctag></lex>
<lex><base>ten</base><ctag>adj:sg:acc:n:pos</ctag></lex>
<lex><base>to</base><ctag>conj</ctag></lex>
<lex><base>to</base><ctag>pred</ctag></lex>
<lex><base>to</base><ctag>qub</ctag></lex>
<lex><base>to</base><ctag>subst:sg:nom:n</ctag></lex>
<lex><base>to</base><ctag>subst:sg:acc:n</ctag></lex>
<lex><base>to</base><ctag>subst:sg:voc:n</ctag></lex>
<ann chan="capitalized_noun" head="1">1</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<tok>
<orth>Wyżyna</orth>
<lex><base>wyżyna</base><ctag>subst:sg:nom:f</ctag></lex>
<ann chan="capitalized_noun" head="1">2</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<tok>
<orth>Płaska</orth>
<lex><base>płaski</base><ctag>adj:sg:nom:f:pos</ctag></lex>
<ann chan="capitalized_noun" head="1">3</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based" head="1">1</ann>
</tok>
<ns/>
<tok>
<orth>,</orth>
<lex><base>,</base><ctag>interp</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<tok>
<orth>Wyżyna</orth>
<lex><base>wyżyna</base><ctag>subst:sg:nom:f</ctag></lex>
<ann chan="capitalized_noun" head="1">4</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<tok>
<orth>Wypukła</orth>
<lex><base>wypukły</base><ctag>adj:sg:nom:f:pos</ctag></lex>
<ann chan="capitalized_noun" head="1">5</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based" head="1">2</ann>
</tok>
<ns/>
<tok>
<orth>,</orth>
<lex><base>,</base><ctag>interp</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<tok>
<orth>wyżyna</orth>
<lex><base>wyżyna</base><ctag>subst:sg:nom:f</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<tok>
<orth>Kot</orth>
<lex><base>kot</base><ctag>subst:sg:nom:m2</ctag></lex>
<ann chan="capitalized_noun" head="1">7</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word" head="1">1</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<tok>
<orth>i</orth>
<lex><base>i</base><ctag>conj</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<tok>
<orth>miasto</orth>
<lex><base>miasto</base><ctag>subst:sg:nom:n</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger" head="1">1</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<tok>
<orth>Gdańsk</orth>
<lex><base>gdańsk</base><ctag>subst:sg:nom:m3</ctag></lex>
<ann chan="capitalized_noun" head="1">8</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word" head="1">2</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<ns/>
<tok>
<orth>.</orth>
<lex><base>.</base><ctag>interp</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
</sentence>
</chunk>
</chunkList>
</cesAna>
apply(
match(
regex( base[0], 'wyżyna' ),
is( 'reladj_gaz_based' )
),
cond(
ann(:1, 'capitalized_noun' ),
equal( nmb[first(:1)], nmb[first(:2)] ),
equal( cas[first(:1)], cas[first(:2)] ),
equal( gnd[first(:1)], gnd[first(:2)] )
),
actions(
mark(M, 'HIGHLAND_NAM')
)
)
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE cesAna SYSTEM "xcesAnaIPI.dtd">
<cesAna xmlns:xlink="http://www.w3.org/1999/xlink" version="1.0" type="lex disamb">
<chunkList>
<chunk>
<sentence>
<tok>
<orth>To</orth>
<lex><base>ten</base><ctag>adj:sg:nom:n:pos</ctag></lex>
<lex><base>ten</base><ctag>adj:sg:acc:n:pos</ctag></lex>
<lex><base>to</base><ctag>conj</ctag></lex>
<lex><base>to</base><ctag>pred</ctag></lex>
<lex><base>to</base><ctag>qub</ctag></lex>
<lex><base>to</base><ctag>subst:sg:nom:n</ctag></lex>
<lex><base>to</base><ctag>subst:sg:acc:n</ctag></lex>
<lex><base>to</base><ctag>subst:sg:voc:n</ctag></lex>
<ann chan="capitalized_noun" head="1">1</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="HIGHLAND_NAM">0</ann>
</tok>
<tok>
<orth>Wyżyna</orth>
<lex><base>wyżyna</base><ctag>subst:sg:nom:f</ctag></lex>
<ann chan="capitalized_noun" head="1">2</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="HIGHLAND_NAM" head="1">1</ann>
</tok>
<tok>
<orth>Płaska</orth>
<lex><base>płaski</base><ctag>adj:sg:nom:f:pos</ctag></lex>
<ann chan="capitalized_noun" head="1">3</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based" head="1">1</ann>
<ann chan="HIGHLAND_NAM">1</ann>
</tok>
<ns/>
<tok>
<orth>,</orth>
<lex><base>,</base><ctag>interp</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="HIGHLAND_NAM">0</ann>
</tok>
<tok>
<orth>Wyżyna</orth>
<lex><base>wyżyna</base><ctag>subst:sg:nom:f</ctag></lex>
<ann chan="capitalized_noun" head="1">4</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="HIGHLAND_NAM" head="1">2</ann>
</tok>
<tok>
<orth>Wypukła</orth>
<lex><base>wypukły</base><ctag>adj:sg:nom:f:pos</ctag></lex>
<ann chan="capitalized_noun" head="1">5</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based" head="1">2</ann>
<ann chan="HIGHLAND_NAM">2</ann>
</tok>
<ns/>
<tok>
<orth>,</orth>
<lex><base>,</base><ctag>interp</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="HIGHLAND_NAM">0</ann>
</tok>
<tok>
<orth>wyżyna</orth>
<lex><base>wyżyna</base><ctag>subst:sg:nom:f</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="HIGHLAND_NAM">0</ann>
</tok>
<tok>
<orth>Kot</orth>
<lex><base>kot</base><ctag>subst:sg:nom:m2</ctag></lex>
<ann chan="capitalized_noun" head="1">7</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word" head="1">1</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="HIGHLAND_NAM">0</ann>
</tok>
<tok>
<orth>i</orth>
<lex><base>i</base><ctag>conj</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<tok>
<orth>miasto</orth>
<lex><base>miasto</base><ctag>subst:sg:nom:n</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger" head="1">1</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<tok>
<orth>Gdańsk</orth>
<lex><base>gdańsk</base><ctag>subst:sg:nom:m3</ctag></lex>
<ann chan="capitalized_noun" head="1">8</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word" head="1">2</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<ns/>
<tok>
<orth>.</orth>
<lex><base>.</base><ctag>interp</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
</sentence>
</chunk>
</chunkList>
</cesAna>
apply(
match(
regex( base[0], 'wyżyna'),
and( inter(class[0], {subst}), inter(cas[0], {nom}) )
),
cond(
not( ann(:1, 'capitalized_noun' ) )
),
actions(
mark(:2, 'HIGHLAND_NAM')
)
)
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE cesAna SYSTEM "xcesAnaIPI.dtd">
<cesAna xmlns:xlink="http://www.w3.org/1999/xlink" version="1.0" type="lex disamb">
<chunkList>
<chunk>
<sentence>
<tok>
<orth>To</orth>
<lex><base>ten</base><ctag>adj:sg:nom:n:pos</ctag></lex>
<lex><base>ten</base><ctag>adj:sg:acc:n:pos</ctag></lex>
<lex><base>to</base><ctag>conj</ctag></lex>
<lex><base>to</base><ctag>pred</ctag></lex>
<lex><base>to</base><ctag>qub</ctag></lex>
<lex><base>to</base><ctag>subst:sg:nom:n</ctag></lex>
<lex><base>to</base><ctag>subst:sg:acc:n</ctag></lex>
<lex><base>to</base><ctag>subst:sg:voc:n</ctag></lex>
<ann chan="capitalized_noun" head="1">1</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="HIGHLAND_NAM">0</ann>
</tok>
<tok>
<orth>Wyżyna</orth>
<lex><base>wyżyna</base><ctag>subst:sg:nom:f</ctag></lex>
<ann chan="capitalized_noun" head="1">2</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="HIGHLAND_NAM">0</ann>
</tok>
<tok>
<orth>Płaska</orth>
<lex><base>płaski</base><ctag>adj:sg:nom:f:pos</ctag></lex>
<ann chan="capitalized_noun" head="1">3</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based" head="1">1</ann>
<ann chan="HIGHLAND_NAM">0</ann>
</tok>
<ns/>
<tok>
<orth>,</orth>
<lex><base>,</base><ctag>interp</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="HIGHLAND_NAM">0</ann>
</tok>
<tok>
<orth>Wyżyna</orth>
<lex><base>wyżyna</base><ctag>subst:sg:nom:f</ctag></lex>
<ann chan="capitalized_noun" head="1">4</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="HIGHLAND_NAM">0</ann>
</tok>
<tok>
<orth>Wypukła</orth>
<lex><base>wypukły</base><ctag>adj:sg:nom:f:pos</ctag></lex>
<ann chan="capitalized_noun" head="1">5</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based" head="1">2</ann>
<ann chan="HIGHLAND_NAM">0</ann>
</tok>
<ns/>
<tok>
<orth>,</orth>
<lex><base>,</base><ctag>interp</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="HIGHLAND_NAM">0</ann>
</tok>
<tok>
<orth>wyżyna</orth>
<lex><base>wyżyna</base><ctag>subst:sg:nom:f</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="HIGHLAND_NAM">0</ann>
</tok>
<tok>
<orth>Kot</orth>
<lex><base>kot</base><ctag>subst:sg:nom:m2</ctag></lex>
<ann chan="capitalized_noun" head="1">7</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word" head="1">1</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="HIGHLAND_NAM" head="1">1</ann>
</tok>
<tok>
<orth>i</orth>
<lex><base>i</base><ctag>conj</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<tok>
<orth>miasto</orth>
<lex><base>miasto</base><ctag>subst:sg:nom:n</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger" head="1">1</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<tok>
<orth>Gdańsk</orth>
<lex><base>gdańsk</base><ctag>subst:sg:nom:m3</ctag></lex>
<ann chan="capitalized_noun" head="1">8</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word" head="1">2</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
<ns/>
<tok>
<orth>.</orth>
<lex><base>.</base><ctag>interp</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
</tok>
</sentence>
</chunk>
</chunkList>
</cesAna>
apply(
match(
is( 'city_trigger' ),
is( 'first_capital_word' )
),
cond(
not( annsub(:2, 'city_nam_gaz') )
),
actions(
mark(:2, 'CITY_NAM')
)
)
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE cesAna SYSTEM "xcesAnaIPI.dtd">
<cesAna xmlns:xlink="http://www.w3.org/1999/xlink" version="1.0" type="lex disamb">
<chunkList>
<chunk>
<sentence>
<tok>
<orth>To</orth>
<lex><base>ten</base><ctag>adj:sg:nom:n:pos</ctag></lex>
<lex><base>ten</base><ctag>adj:sg:acc:n:pos</ctag></lex>
<lex><base>to</base><ctag>conj</ctag></lex>
<lex><base>to</base><ctag>pred</ctag></lex>
<lex><base>to</base><ctag>qub</ctag></lex>
<lex><base>to</base><ctag>subst:sg:nom:n</ctag></lex>
<lex><base>to</base><ctag>subst:sg:acc:n</ctag></lex>
<lex><base>to</base><ctag>subst:sg:voc:n</ctag></lex>
<ann chan="capitalized_noun" head="1">1</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="CITY_NAM">0</ann>
</tok>
<tok>
<orth>Wyżyna</orth>
<lex><base>wyżyna</base><ctag>subst:sg:nom:f</ctag></lex>
<ann chan="capitalized_noun" head="1">2</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="CITY_NAM">0</ann>
</tok>
<tok>
<orth>Płaska</orth>
<lex><base>płaski</base><ctag>adj:sg:nom:f:pos</ctag></lex>
<ann chan="capitalized_noun" head="1">3</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based" head="1">1</ann>
<ann chan="CITY_NAM">0</ann>
</tok>
<ns/>
<tok>
<orth>,</orth>
<lex><base>,</base><ctag>interp</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="CITY_NAM">0</ann>
</tok>
<tok>
<orth>Wyżyna</orth>
<lex><base>wyżyna</base><ctag>subst:sg:nom:f</ctag></lex>
<ann chan="capitalized_noun" head="1">4</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="CITY_NAM">0</ann>
</tok>
<tok>
<orth>Wypukła</orth>
<lex><base>wypukły</base><ctag>adj:sg:nom:f:pos</ctag></lex>
<ann chan="capitalized_noun" head="1">5</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based" head="1">2</ann>
<ann chan="CITY_NAM">0</ann>
</tok>
<ns/>
<tok>
<orth>,</orth>
<lex><base>,</base><ctag>interp</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="CITY_NAM">0</ann>
</tok>
<tok>
<orth>wyżyna</orth>
<lex><base>wyżyna</base><ctag>subst:sg:nom:f</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="CITY_NAM">0</ann>
</tok>
<tok>
<orth>Kot</orth>
<lex><base>kot</base><ctag>subst:sg:nom:m2</ctag></lex>
<ann chan="capitalized_noun" head="1">7</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word" head="1">1</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="CITY_NAM">0</ann>
</tok>
<tok>
<orth>i</orth>
<lex><base>i</base><ctag>conj</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="CITY_NAM">0</ann>
</tok>
<tok>
<orth>miasto</orth>
<lex><base>miasto</base><ctag>subst:sg:nom:n</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger" head="1">1</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="CITY_NAM">0</ann>
</tok>
<tok>
<orth>Gdańsk</orth>
<lex><base>gdańsk</base><ctag>subst:sg:nom:m3</ctag></lex>
<ann chan="capitalized_noun" head="1">8</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word" head="1">2</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="CITY_NAM" head="1">1</ann>
</tok>
<ns/>
<tok>
<orth>.</orth>
<lex><base>.</base><ctag>interp</ctag></lex>
<ann chan="capitalized_noun">0</ann>
<ann chan="city_trigger">0</ann>
<ann chan="first_capital_word">0</ann>
<ann chan="reladj_gaz_based">0</ann>
<ann chan="CITY_NAM">0</ann>
</tok>
</sentence>
</chunk>
</chunkList>
</cesAna>
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment