# Small sample corpus for Semco consisting of 10 simplified sentences from
# the NANLT conversion of the Penn Treebank WSJ corpus generated by adapt-wsj.

# Header of the first source file:

# *x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*
# *x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*
# *x*                                                                     *x*
# *x*            Copyright (C) 1991 University of Pennsylvania            *x*
# *x*                                                                     *x*
# *x*    The data in this file are part of a preliminary version of the   *x*
# *x*    Penn Treebank Corpus and should not be redistributed.  Any       *x*
# *x*    research using this corpus or based on it should acknowledge     *x*
# *x*    that fact, as well as the preliminary nature of the corpus.      *x*
# *x*                             (9/9/1991)                             *x*
# *x*                                                                     *x*
# *x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*
# *x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*x*

# Sentence 1

[ [S [NP
Pierre Pierre_NP1:1 
Vinken Vinken_NP1:1 
]
will will_NN1:7.7614e-05 will_VM:0.999922 
[VP
join join_VV0:1 
[NP
the the_RR:1.98572e-06 the_II:0.00010493 the_DD1:9.73928e-05 the_DD:0.00151109 the_AT:0.998285 
board board_NNJ1:0.0605852 board_NN1:0.93938 board_VV0:3.48734e-05 
]
[PP
as as_VBZ:0.00320503 as_CSA:0.230434 as_II:0.70739 as_CC:0.0430696 as_CST:0.00112541 as_CS:0.00245221 as_RR:0.00131474 as_RG:0.0110083 
[NP
a a_DD:0.000659215 a_&FO:3.95852e-05 a_DD1:0.00229106 a_DD2:0.000199383 a_AT1:0.996805 a_ZZ1:5.53294e-06 
nonexecutive nonexecutive_JJ:1 
director director_NN1:1 
]]]]
. ._.:1 
]

# Sentence 2

[ [S [NP
Mr. Mr._NP1:0.370905 mr._NNS:0.629095 
Vinken Vinken_NP1:1 
]
[VP
is be+s_VBZ:0.0285321 be+s_VVZ:0.971461 is_REX:2.22507e-308 is+s_NN2:6.44226e-06 
[NP
chairman chairman_NNS1:0.00213974 chairman_NN1:0.99786 
[PP
of of_RG:2.22588e-308 of_II:0.0171258 of_CC:0.000247425 of_RR:5.83938e-05 of_IO:0.982568 
[NP [NP
Elsevier Elsevier_NP1:1 
N.V. N.v._NP1:1 
]
, ,_,:1 
[NP
the the_RR:0.000215024 the_II:0.000132255 the_DD1:5.84507e-05 the_DD:0.000552031 the_AT:0.999042 
Dutch dutch_JJ:0.980359 Dutch_NP1:0.0196407 Dutch_NP2:1.42603e-307 
publishing publish+ing_VVG:0.0775149 publishing_NN1:0.922485 
group group_NNJ1:0.0782544 group_VV0:6.62987e-05 group_NN1:0.921679 
]]]]]]
. ._.:1 
]

# Sentence 3

[ [S [NP
Rudolph Rudolph_NP1:1 
Agnew Agnew_NP1:1 
]
was be+ed_VVD:0.0931363 be+ed_VBDZ:0.906864 
[VP
named name+ed_VVN:0.992719 name+ed_VVD:0.00728119 
[NP
a a_DD:0.00116185 a_&FO:3.21577e-05 a_DD1:0.000784802 a_DD2:0.000223826 a_AT1:0.997738 a_ZZ1:5.92931e-05 
nonexecutive nonexecutive_JJ:1 
director director_NN1:1 
[PP
of of_RG:2.44196e-06 of_II:0.0304114 of_CC:0.000101733 of_RR:0.000137705 of_IO:0.969347 
[NP
this this_DD1:1 
[ADJP
British british_NN2:9.95037e-307 British_NP1:0.00615174 British_NP2:2.22507e-308 british_JJ:0.993848 
]
industrial industrial_JJ:1 
conglomerate conglomerate_JJ:0.00707051 conglomerate_NN1:0.992929 
]]]]]
. ._.:1 
]

# Sentence 4

[ [S [NP
A a_&FO:0.00861901 a_DD1:0.0131785 a_DD2:0.0159101 a_AT1:0.879206 a_DD:0.0295958 a_NNU:0.0534909 
form form_VV0:0.000662201 form_NN1:0.999338 
[PP
of of_RG:1.07332e-06 of_II:0.00863746 of_CC:0.000124222 of_RR:2.11766e-05 of_IO:0.991216 
[NP
asbestos asbestos_NN1:1 
]]]
has have+s_VV0:2.90454e-05 have+s_VHZ:0.891285 have+s_VVZ:0.108594 have+s_VVN:2.43604e-05 ha+s_NN1:6.74572e-05 
[VP
caused cause+ed_VVN:0.999933 cause+ed_VVD:6.73624e-05 
[NP
a a_DD:0.00117714 a_&FO:3.35924e-05 a_DD1:0.000787991 a_DD2:0.00022333 a_AT1:0.997716 a_ZZ1:6.18211e-05 
high high_JJ:0.991876 high_RR:0.000112578 high_NN1:0.00801145 
percentage percentage_NN1:1 
[PP
of of_RG:1.01931e-06 of_II:0.00853608 of_CC:0.000123881 of_RR:2.05286e-05 of_IO:0.991318 
[NP
cancer cancer_NN1:1 
deaths death+s_NN2:1 
]]
[PP
among among_II:1 
[NP
a a_DD:0.00112896 a_&FO:0.000202097 a_DD1:0.00577021 a_DD2:3.78017e-05 a_AT1:0.992839 a_ZZ1:2.16712e-05 
group group_NNJ1:0.0327462 group_VV0:1.59755e-06 group_NN1:0.967252 
[PP
of of_RG:2.22581e-308 of_II:0.00748196 of_CC:0.000160622 of_RR:3.48695e-05 of_IO:0.992323 
[NP [NP
workers worker+s_NN2:1 
]
[VP
exposed exposed_JJ:0.000604052 expose+ed_VVN:0.925379 expose+ed_VVD:0.074017 
[PP
to to_RL:0.000125345 to_II:0.99948 to_TO:3.13906e-306 to_RR:0.000394876 to_RG:2.6286e-308 
[NP
it it_PPH1:1 
]]]]]]]]]]
. ._.:1 
]

# Sentence 5

[ [S [NP
The the_DD:0.0660853 the_AT:0.933915 
asbestos asbestos_NN1:1 
fiber fiber_NN1:1 
]
[VP
is be+s_VBZ:0.184367 be+s_VVZ:0.815614 is_REX:2.41188e-308 is+s_NN2:1.92191e-05 
[ADJP
unusually unusually_RR:1 
resilient resilient_JJ:1 
]
[SBAR
once once_CS:0.654555 once_RR:0.345445 
[S [NP
it it_PPH1:1 
]
[VP
enters enter+s_VVZ:1 
[NP
the the_RR:6.9011e-06 the_II:0.00016854 the_DD1:2.22666e-308 the_DD:0.00294316 the_AT:0.996881 
lungs lung+s_NN2:1 
]]]]]]
. ._.:1 
]

# Sentence 6

[ [S [NP
Lorillard Lorillard_NP1:0.998084 lorillard_NN1:0.00191604 
Inc. inc._NN1:0.000262692 Inc._NP1:0.999724 inc._JJ:1.29575e-05 
]
[VP
stopped stop+ed_VVN:0.11759 stop+ed_VVD:0.88241 
[VP
using use+ing_VVG:1 
[NP
crocidolite crocidolite_NN1:1 
]
[PP
in in_BTO:2.25441e-308 in_RP:0.00267377 in_CS:0.000560184 in_RR:0.000206836 in_II:0.996559 
[NP
its its_APP$:1 
Micronite micronite_NN1:1 
cigarette cigarette_NN1:1 
filters filter+s_VVZ:0.21741 filter+s_NN2:0.78259 
]]]
[PP
in in_BTO:2.22507e-308 in_RP:0.0050993 in_CS:8.77927e-05 in_RR:0.0013341 in_II:0.993479 
[NP
1956 1956_&FO:0.00802015 1956_NN:0.000850186 1956_MC:0.935895 1956_MD:0.00251412 1956_MC1:0.04989 1956_MF:2.22507e-308 1956_MC2:9.12446e-306 1956_NN2:0.000404501 1956_NP1:0.00203585 1956_NP2:0.000390383 
]]]]
. ._.:1 
]

# Sentence 7

[ [SBAR
Although although_CS:1 
[S [NP
preliminary preliminary_JJ:1 
findings finding+s_NN2:1 
]
were be+ed_VVD:0.0151409 be+ed_VBDR:0.984859 
[VP
reported reported_JJ:0.000370661 report+ed_VVN:0.995247 report+ed_VVD:0.00438208 
[ADVP [NP
more more_JJR:0.00140618 more_DAR:0.0793364 more_JJ:1.01938e-05 more_RR:1.48395e-05 more_RRR:0.919232 
[PP
than than_II:0.000346366 than_CSN:0.999643 than_RR:1.06566e-05 
[NP [ADVP [NP
a a_DD:0.00587354 a_&FO:0.000182448 a_DD1:0.0282999 a_DD2:3.3273e-05 a_AT1:0.965611 a_ZZ1:7.3289e-09 
year year_NN1:0.358986 year_NNT1:0.641014 
]
ago ago_RA:1 
]]]]]]]
, ,_,:1 
[S [NP
the the_RR:2.95934e-07 the_II:1.61761e-07 the_DD1:1.35257e-05 the_DD:7.62749e-07 the_AT:0.999985 
[ADJP
latest latest_JJT:0.99864 latest_JJ:0.00135976 
]
results result+s_VVZ:2.22507e-308 result+s_NN2:1 
]
[VP
appear appear_VV0:1 
[PP
in in_BTO:2.22507e-308 in_RP:0.146927 in_CS:0.000433618 in_RR:0.00179492 in_II:0.850845 
[NP [NP [NP
today today_RR:3.59187e-05 today_RT:0.244416 today_NN1:0.755548 
]
's be+s_VBZ:0.0501271 's+_$:0.945769 as+_CSA:0.00347898 do+s_VDZ:0.000599521 's_PPIO2:2.22507e-308 have+s_VHZ:2.56581e-05 
[NP
New New_NP1:0.987702 New_NP2:2.22507e-308 new_JJ:0.0122984 
England England_NP1:1 
Journal journal_NN1:0.0112921 Journal_NP1:0.988708 
[PP
of of_RG:4.25765e-07 of_II:0.0516924 of_CC:0.00247593 of_RR:0.000457553 of_IO:0.945374 
[NP
Medicine medicine_NN1:0.0869097 Medicine_NP1:0.91309 
]]]]]]]]]
. ._.:1 
]

# Sentence 8

[ [S [NP
A a_&FO:0.00718197 a_DD1:0.0117619 a_DD2:0.0130977 a_AT1:0.89692 a_DD:0.026407 a_NNU:0.0446316 
Lorillard Lorillard_NP1:0.166176 lorillard_NN1:0.833824 
spokewoman spokewoman_NN1:1 
]
[VP
said say+ed_VVN:0.00886117 say+ed_VVD:0.991139 
]
, ,_,:1 
`` ``_VVG:0.301924 ``_VV0:0.139409 ``_JJ:0.0126761 ``_VVZ:0.0415823 ``_RR:0.11422 ``_VVN:0.0151941 ``_NN1:0.0150909 ``_NN2:0.00564269 ``_VVD:0.349482 ``_MC:0.00477821 
[S [NP
This this_DD1:1 
]
[VP
is be+s_VBZ:0.376624 be+s_VVZ:0.623376 is_REX:2.22507e-308 is+s_NN2:2.42955e-308 
[NP
an an_AT1:1 
old old_JJ:1 
story story_NN1:1 
]]]]
. ._.:1 
]

# Sentence 9

[ [S [NP
We we_PPIS2:1 
]
're be+_VV0:0.198654 be+_VBR:0.801346 
[VP
talking talking_NN1:0.00158724 talk+ing_VVG:0.998413 
[PP
about about_RPK:1.20317e-305 about_RG:1.2802e-306 about_II:1 
[NP [ADVP [NP
years year+s_NNT2:0.929554 year+s_NN2:0.0704462 
]
ago ago_RA:1 
]
[SBAR
before before_ICS:0.99345 before_RR:0.00655014 
[S [NP
anyone anyone_PN1:0.578578 anyone_NN1:0.421422 
]
[VP
heard hear+ed_VVN:0.564645 hear+ed_VVD:0.435355 
[PP
of of_RG:7.72216e-05 of_II:0.251921 of_CC:0.000615334 of_RR:0.00124504 of_IO:0.746141 
[S [NP
asbestos asbestos_NN1:1 
]
[VP
having have+ing_VHG:0.806797 have+ing_VVG:0.193203 
[NP
any any_DD:1 
questionable questionable_JJ:1 
properties property+s_NN2:1 
]]]]]]]]]]]
. ._.:1 
]

# Sentence 10

[ [S [NP
There there_EX:0.997201 there_RL:0.0027986 
]
[VP
is be+s_VBZ:0.782589 be+s_VVZ:0.217411 is_REX:5.0987e-308 is+s_NN2:1.31014e-09 
[NP
no no_RR:0.000177406 no_DDQV:5.03107e-306 no_UH:2.32961e-308 no_AT:0.999823 
asbestos asbestos_NN1:1 
[PP
in in_BTO:2.25441e-308 in_RP:0.00267377 in_CS:0.000560184 in_RR:0.000206836 in_II:0.996559 
[NP
our our_APP$:1 
products product+s_NN2:1 
]]]
now now_JJ:0.000104179 now_CS:2.29442e-308 now_RR:0.630971 now_RT:0.368924 
]]
. ._.:1 
]
