854100091ef9dd877d959643e9b10b5b4eea5e0c
neural network, bag of words neural-network bow
- challenge
- Challenging America word-gap prediction
- submitter
- s444356
- submitted
- 2023-05-30 14:53:52.968152 UTC
- original repo
https://git.wmi.amu.edu.pl/s444356/challenging-america-word-gap-prediction
/ branchmaster
- publicly available at
git://gonito.net/challenging-america-word-gap-prediction
/ branchsubmission-08620
- browsable at
- https://gonito.net/gitlist/challenging-america-word-gap-prediction.git/submission-08620/
- clone by
git clone --single-branch git://gonito.net/challenging-america-word-gap-prediction -b submission-08620
- file basename
- out
Parameter | Value |
---|---|
batch-size | 10000 |
context-size | 25 |
dropout | 0.3 |
embed-size | 200 |
epochs | 1 |
hidden-size | 1000 |
hidden-size_2 | 500 |
learning-rate | 1.0e-3 |
top | 10 |
vocab-size | 25000 |
test-A / e926e7439c63a2c7b31ce85d637d70b92449a545
Metric | Score |
---|---|
PerplexityHashed | 134.70 |
dev-0 / a3f72d65e4d5b95fc14e31aa45ead633605b9d61
Metric | Score |
---|---|
PerplexityHashed | 125.69 |
worst items
note: the gold standard is taken from the submission itself, not from the challenge data!# | input | expected output | actual output | test-A PerplexityHashed |
---|---|---|---|---|
1 | 0232b56b76d6643716be358274b00b6f THE HOPE PIONEER ChronAm 1893.9164383244547 47.32221 -97.72232 '"®ty. and recorded as a Mortgage In the oll… | iu., | m:0.9937 ni:0.0035 M:0.0013 in:0.0007 :0.0004 tn:0.0001 ra:0.0001 p:0.0001 In:0.0001 oclock:0.0000 | 2560000.00 |
2 | 05f5fc6c60a00bd384ecebe40bf59d87 COURIER DEMOCRAT ChronAm 1909.0178081874683 48.76059 -98.367824 Notice is hereby given. That that certain\n… | A. | A:0.9985 D:0.0003 S:0.0001 P:0.0001 :0.0005 a:0.0001 from:0.0001 X:0.0001 W:0.0001 I:0.0000 | 2047795.20 |
3 | 3f3293b0ce21c2006c76b981a3bcac36 THE WICHITA CITY EAGLE ChronAm 1874.2890410641805 37.692236 -97.337545 Leave Medicine Lodge Thursday a 7 a.… | p. | p:0.6148 a:0.3812 by:0.0013 A:0.0010 n:0.0004 r:0.0003 am:0.0001 s:0.0001 P:0.0001 :0.0008 | 1280128.00 |
4 | 0e826a9041caededa070fb4c285bf8cf THE WICHITA CITY EAGLE ChronAm 1882.9136985984271 37.692236 -97.337545 alter ease of Kulield rillcs with sw… | o'clock | oclock:0.9894 noon:0.0034 midnight:0.0027 clock:0.0013 :0.0022 p:0.0005 dusk:0.0003 and:0.0002 feet:0.0001 two:0.0001 | 465547.64 |
5 | 07e679bf097f195dc2c8bb27d7ad44a5 LOS ANGELES HERALD ChronAm 1891.3575342148656 34.054935 -118.244476 The regular Saturday evening hop\nwas w… | Mrs. | Mrs:0.9615 Mr:0.0150 Mra:0.0104 Mis:0.0064 Miss:0.0022 Rev:0.0011 :0.0026 Prof:0.0004 Airs:0.0003 Hon:0.0002 | 393885.54 |
6 | 0a1661ff6d5076299f4fbb72b63e45ff RAFTSMAN'S JOURNAL ChronAm 1867.1767122970573 41.02728 -78.439188 Also A certain tract of land situate in D… | beginning, | beginning:0.9942 land:0.0013 lot:0.0008 :0.0027 alley:0.0003 ground:0.0002 laud:0.0002 road:0.0001 residence:0.0001 ditch:0.0001 | 379259.26 |
7 | 8972157574e4b774d8ed5beaa441e2c3 RICHMOND ENQUIRER ChronAm 1842.815068461441 37.538509 -77.43428 The improvements consist of a small dwellin… | tlun | than:0.9916 tban:0.0013 thau:0.0010 titan:0.0009 tlian:0.0007 to:0.0005 thnn:0.0004 tnan:0.0004 or:0.0003 exceeding:0.0002 | 379259.26 |
8 | 01cba6f9ccafee50cfe13d363b94003c RICHMOND ENQUIRER ChronAm 1819.0698629819888 37.538509 -77.43428 of that gentleman which has pointed the da… | gen- | gen:0.9905 Fed:0.0020 Gen:0.0011 :0.0046 ap:0.0005 Commis:0.0004 min:0.0003 ma:0.0002 Ap:0.0002 sol:0.0002 | 222608.70 |
9 | 2efb916d2aab3933a0423f697b858740 THE DICKINSON PRESS ChronAm 1910.8068492833586 46.879176 -102.789624 West; thence north up to and along the… | or | of:0.9678 ot:0.0155 ol:0.0039 oi:0.0020 between:0.0019 o:0.0018 cf:0.0009 to:0.0008 ofthe:0.0007 :0.0047 | 217872.34 |
10 | 0e6841bc63dc4256a9c924c234cdcaeb EVENING CAPITAL ChronAm 1903.828767091578 38.97864 -76.492786 At St. Joseph’s Hospital.\nMr. P. B. Bowdoin,… | neces- | neces:0.9942 :0.0048 conclu:0.0002 ev:0.0002 inten:0.0001 occa:0.0001 nat:0.0001 commis:0.0001 oppor:0.0001 the:0.0001 | 213333.33 |
11 | 3ff22426092d3a6869b2bd48364ba5f2 RAFTSMAN'S JOURNAL ChronAm 1858.9356164066464 41.02728 -78.439188 aware that the earliest and the best frui… | tages. | tages:0.7243 tage:0.2697 :0.0050 der:0.0002 tons:0.0002 ton:0.0001 ces:0.0001 sons:0.0001 er:0.0001 mies:0.0001 | 204779.52 |
12 | 12eb8650fe054cdfbcf101899590a01a CLARKSVILLE CHRONICLE ChronAm 1859.4972602422629 36.527761 -87.35887 or road ; on the east by a street or a… | Cir- | Cir:0.9098 cir:0.0807 :0.0055 the:0.0014 bu:0.0007 Grand:0.0006 ter:0.0004 Juno:0.0004 The:0.0003 mid:0.0002 | 186181.82 |
13 | 3945dffe91dbb1dc53aead1445a27603 THE NEW NORTH-WEST ChronAm 1871.9575342148655 46.395761 -112.730038 Ytvirtue o an order and decree Isued ou… | Counrt | Court:0.9712 court:0.0119 Conrt:0.0062 :0.0060 City:0.0020 Courthouse:0.0008 ourt:0.0006 city:0.0006 White:0.0004 Mansion:0.0002 | 170649.60 |
14 | 851768ce6f1e04724f2c28c9dfe84887 THE NEW NORTH-WEST ChronAm 1871.1684931189752 46.395761 -112.730038 PUBLIC NOTICE is hereby given that on t… | A. | A:0.9864 S:0.0015 a:0.0014 :0.0069 AD:0.0012 D:0.0012 W:0.0004 N:0.0004 P:0.0004 p:0.0004 | 148435.48 |
15 | 0c2196a34e9901dfbe5ad9259263bc2f ARIZONA REPUBLICAN ChronAm 1912.7117486022566 33.448587 -112.077346 3. That a cement concrete curb be\nbuil… | par- | par:0.9838 :0.0071 neces:0.0024 fa:0.0022 quali:0.0017 facili:0.0007 satis:0.0007 funda:0.0006 ele:0.0004 particu:0.0003 | 144210.93 |
16 | 0b3f1e51f2cf34a3e4c83384b5d193ae THE MEMPHIS APPEAL ChronAm 1887.0671232559614 35.149022 -90.051628 The Coahoma, from O.'ceoU.bronght\n14 ba… | tt) | to:0.7167 from:0.2524 via:0.0094 into:0.0049 in:0.0017 for:0.0016 the:0.0013 at:0.0012 toward:0.0010 by:0.0008 | 113777.78 |
17 | 32510d2ec2b19ad0b20ad16ee28b17b0 THE EMPIRE COUNTY ARGUS ChronAm 1856.8346994219287 38.799901 -120.890216 Messrs. Editors :—One more week wi… | Demo- | Demo:0.7038 demo:0.2838 :0.0095 citi:0.0011 pol:0.0006 Re:0.0003 poli:0.0003 popu:0.0003 judi:0.0001 intelli:0.0001 | 107778.69 |
18 | c23e0b1d0ce15db1d62271289c0d82aa RAFTSMAN'S JOURNAL ChronAm 1864.4549180011638 41.02728 -78.439188 machine, and six small houses erected the… | de- | de:0.9820 :0.0103 De:0.0017 dc:0.0014 ar:0.0014 af:0.0007 Pa:0.0007 Sur:0.0006 in:0.0006 Ar:0.0006 | 99417.48 |
19 | e11d5304f5e0f716206d72f21e2d8b3d RICHMOND ENQUIRER ChronAm 1817.6315068176052 37.538509 -77.43428 By the brig Henry, from Havana, the Editor… | re- | re:0.9196 ac:0.0575 pro:0.0030 ob:0.0024 trans:0.0022 sup:0.0017 rt:0.0016 :0.0105 im:0.0008 r:0.0007 | 97523.81 |
20 | 1ef4f5e00de54cfbc0786c63fc0ee4ea THE DICKINSON PRESS ChronAm 1894.2260273655504 46.879176 -102.789624 As the fortune of war has favored his\… | the | of:0.9604 ot:0.0127 ol:0.0053 oi:0.0025 cf:0.0025 or:0.0010 o:0.0010 and:0.0010 with:0.0008 f:0.0008 | 85333.33 |
21 | 21a4004987635d163f83641f4f115d48 THE DICKINSON PRESS ChronAm 1897.905479420345 46.879176 -102.789624 Ill Groceries\n» We carry a full and co… | bs | be:0.9357 bo:0.0196 he:0.0143 lie:0.0072 b:0.0058 le:0.0022 oe:0.0011 become:0.0010 :0.0122 bc:0.0008 | 83926.03 |
22 | 12053b3589509ff26b86805ecd91fd2e COURIER DEMOCRAT ChronAm 1906.987671201167 48.76059 -98.367824 Notice is hereby given, that that certain\nm… | o'clock | oclock:0.9711 and:0.0050 days:0.0033 clock:0.0028 :0.0124 to:0.0017 years:0.0016 minutes:0.0010 S:0.0007 I:0.0005 | 82588.90 |
23 | 019c8e1ff022be553ae21c8875fb8ad6 ARIZONA REPUBLICAN ChronAm 1904.908469913732 33.448587 -112.077346 The Pathfinder, published in Wash-\ningt… | re- | re:0.9538 ad:0.0125 dis:0.0117 ro:0.0018 Re:0.0017 con:0.0016 im:0.0012 trans:0.0009 pro:0.0009 di:0.0007 | 77575.76 |
24 | 26add1ebd76a90f03e86a0de62248d9b THE NEVADA JOURNAL ChronAm 1860.5505464164644 39.261561 -121.016059 \\irHEREAS, OX THE 9tli DAY ol JILY\nIT… | *>r | or:0.9367 and:0.0367 of:0.0037 one:0.0029 One:0.0026 a:0.0015 said:0.0013 :0.0132 aud:0.0008 Magnetic:0.0006 | 77575.76 |
25 | 2b4578faaa5d040beefbcf8ece106e6e RICHMOND ENQUIRER ChronAm 1816.8483606241145 37.538509 -77.43428 The funds opened and shut todayatth\nsame … | tent | tem:0.9815 :0.0137 tern:0.0028 guage:0.0005 ue:0.0005 sion:0.0003 tion:0.0002 uation:0.0002 dress:0.0002 gate:0.0001 | 74744.53 |
26 | 483b31c888630a6712df48fe6cee758d RICHMOND ENQUIRER ChronAm 1831.2397259956874 37.538509 -77.43428 11. The said superior courts shall have th… | y | ty:0.8217 cil:0.1340 ties:0.0120 :0.0150 tv:0.0082 try:0.0055 ish:0.0019 ter:0.0011 er:0.0003 e:0.0002 | 68259.84 |
27 | 9a23949c6410e0a789c008623c370c36 DEMOCRAT AND SENTINEL ChronAm 1866.891780790208 40.485194 -78.724957 The present President of the United\nS… | States. | States:0.9218 Slates:0.0217 Stales:0.0167 :0.0159 State:0.0063 Kingdom:0.0060 states:0.0047 Statea:0.0035 Stat:0.0023 tates:0.0011 | 64402.52 |
28 | 3e9eb2473cebd9f0e4f87b791c40ccca THE DICKINSON PRESS ChronAm 1917.2835616121258 46.879176 -102.789624 NOTICE IS HEREBY GIVEN That\nunder aut… | Quar | quar:0.9738 :0.0159 Sec:0.0069 deg:0.0012 sec:0.0006 vo:0.0004 I:0.0003 t:0.0003 Range:0.0002 Chap:0.0002 | 64389.64 |
29 | 39bc47b995780f5bd41c50c2273de08b THE NEVADA JOURNAL ChronAm 1860.3784152689234 39.261561 -121.016059 ftivored grape growing regions of Europ… | moun- | cer:0.8853 moun:0.0831 con:0.0075 re:0.0030 :0.0162 w:0.0011 high:0.0010 Cer:0.0010 Cap:0.0009 cur:0.0009 | 63209.88 |
30 | 0349d547b82df2e09f71d292840b48f9 PULLMAN HERALD ChronAm 1896.1051912252074 46.730427 -117.173895 signed by the courts of other states to\nta… | au- | au:0.9095 bu:0.0369 tem:0.0104 an:0.0098 Au:0.0072 An:0.0037 Bu:0.0034 :0.0164 Bis:0.0015 Com:0.0013 | 62445.27 |
31 | 124853eea403ed0491cf68d75bf6d073 COURIER DEMOCRAT ChronAm 1916.5696720995245 48.76059 -98.367824 You are hereby notified that the said above… | notified, | notified:0.9599 ordered:0.0132 satisfied:0.0027 evidence:0.0024 :0.0166 notice:0.0018 proof:0.0015 and:0.0007 given:0.0007 requested:0.0006 | 61692.92 |
32 | 1a9b1795a77d050c3a5914bc4c23a0e0 DEMOCRATIC MESSENGER ChronAm 1919.1438355847285 38.177063 -75.392696 all the following real estate hy the\n… | seip. | seq:0.9148 al:0.0387 als:0.0232 :0.0167 page:0.0027 No:0.0015 ux:0.0010 folio:0.0005 I:0.0004 Nos:0.0004 | 61311.23 |
33 | 337fe30b62e352ab9f11f319f7dbe684 RICHMOND ENQUIRER ChronAm 1820.9275955967921 37.538509 -77.43428 mid -aid, Mia! before Counsel was ca'led 1… | therefore, | that:0.9554 tbat:0.0067 thai:0.0044 if:0.0041 thut:0.0029 hat:0.0029 thal:0.0026 whether:0.0013 tnat:0.0012 why:0.0011 | 58850.57 |
34 | f1479cb9a6256b326867f7c18fb195e5 EVENING CAPITAL ChronAm 1923.3849314751394 38.97864 -76.492786 room dwelling. Numbered . ".5 and 37. wltl\n… | o | on:0.8984 ou:0.0245 in:0.0148 at:0.0112 along:0.0107 upon:0.0074 near:0.0063 In:0.0040 On:0.0026 by:0.0024 | 57853.11 |
35 | 4a834612c3332bb016a5f541e88aba7d RAFTSMAN'S JOURNAL ChronAm 1863.89999996829 41.02728 -78.439188 terial contemplated by the Constitution, ou… | gen- | gen:0.9364 lib:0.0178 sev:0.0122 :0.0179 appro:0.0038 com:0.0031 en:0.0026 defi:0.0025 incom:0.0023 econ:0.0015 | 57212.42 |
36 | 1b593f17221d49d2a980654eeefe752c THE INTERIOR JOURNAL ChronAm 1907.8726027080163 37.53119 -84.661888 in consulting a competent and reliable\… | if | of:0.9466 ot:0.0163 ol:0.0063 or:0.0034 oi:0.0025 cf:0.0018 o:0.0012 without:0.0012 for:0.0011 in:0.0011 | 55351.35 |
37 | 6539e58de66ce4d7b381c39386366011 RICHMOND ENQUIRER ChronAm 1842.0726027080163 37.538509 -77.43428 Your Committee beg leave to remark here, t… | liand.^none | hand:0.4870 side:0.4784 part:0.0040 aide:0.0029 half:0.0024 end:0.0019 Bide:0.0016 baud:0.0013 day:0.0010 basis:0.0008 | 54759.36 |
38 | 24a2e46bd47831994af1ffd16a8bfefc GREAT FALLS DAILY TRIBUNE ChronAm 1920.908469913732 47.504885 -111.291891 Bonds numbered 1 to 7, Inclusive,… | inclusive, | inclusive:0.4766 Inclusive:0.4736 wit:0.0172 each:0.0048 per:0.0024 :0.0189 cents:0.0020 and:0.0018 par:0.0018 January:0.0008 | 54174.48 |
39 | a8ff5ec194533f00737e94e8b450efa4 THE WICHITA CITY EAGLE ChronAm 1872.9467212798522 37.692236 -97.337545 iu developing the diamond mines. Ar-… | .New | New:0.9404 Xew:0.0251 Now:0.0082 :0.0194 Nev:0.0021 Nw:0.0016 Sew:0.0010 Mew:0.0008 the:0.0007 Washington:0.0007 | 52783.51 |
40 | 03dab7360adf2a8d9e3dc5d39f3f8c77 THE DICKINSON PRESS ChronAm 1904.8647540667375 46.879176 -102.789624 Not long ago Dr. J . N. Hirsch, of Chi… | Discovery, | Discovery:0.9578 Co:0.0047 Prescription:0.0041 Association:0.0034 Compound:0.0028 Institute:0.0023 Cure:0.0022 :0.0207 Society:0.0011 Cos:0.… | 49473.55 |