AB Report (Difference)

This page describes the difference in word tokenization for AB between Java and lisp versions. There are 583 different occurrences in six types of causes in 2004 training set. They are details as follows:

  • Expansion errors (8)
    Original stringNew Words (Java)Old Words (Lisp)Source
    ...don't..DO NOTDON
  • 0290: 10738817
  • 0296: 10927969
  • 0298: 11019399
  • ...who'd..WHO WOOULDWHO
  • 0311: 11424476
  • ...doesn't..DOES NOTDOESN
  • 0312: 11467217
  • ...won't..WILL NOTWON
  • 0314: 11519969
  • ...didn't..DID NOTDIDN
  • 0404: 9875250
  • ...wouldn't..WOULD NOTWOULDN
  • 0405: 9892548
  • Remove Copyright at the end ...Copyright... (313)
    • Remove ...CopyrightCopyright...(41)
      • 0284: 10559555, 10559556, 10559557, 10559558, 10559559, 10559560, 10559561, 10559562, 10559563, 10559564, 10559565, 10559566, 10559567, 10559568, 10559569, 10559570, 10559571, 10559572, 10559625, 10559626, 10559627, 10559628, 10559629, 10559630, 10559631, 10559650, 10559659, 10559660, 10559661, 10559662, 10559663, 10559664, 10559665, 10559666, 10559667, 10559668, 10559669, 10559671, 10559672, 10559673, 10559701
    • Remove ...Copyright Copyright...(231)
      • 0285: 10567770, 10567771, 10567772, 10567774, 10567775, 10567777, 10567778, 10567780, 10567781, 10567782, 10567800, 10567806, 10567807, 10567808, 10567809, 10567810, 10567811, 10567826, 10567864, 10567873, 10567875, 10567876, 10567877, 10567878, 10567879, 10567880, 10575179, 10575180, 10575181, 10575182, 10575183, 10575185, 10575186, 10575187, 10575188, 10575189, 10575190, 10575191, 10575192, 10575193, 10575194, 10575196, 10575197, 10575198, 10575199, 10575200, 10575201, 10575202, 10575239, 10575240, 10575241, 10575242, 10575243, 10575244, 10575245, 10575246, 10575247, 10575248, 10575249, 10575250, 10575251, 10575252, 10575253, 10575254, 10575255, 10575256, 10575257, 10575258, 10575259, 10575260, 10575261, 10575262, 10575263, 10575264, 10575272, 10575273, 10575274, 10575275, 10575276, 10575277, 10575291, 10575292, 10575293, 10575294, 10575295, 10575296, 10575297, 10575309, 10575310, 10575311, 10575312, 10575313, 10575314, 10575315, 10575316, 10575317, 10575318, 10575319, 10575320, 10575321, 10575322, 10575323, 10575324, 10575325, 10575326, 10575327, 10575328, 10575329, 10575330, 10575331, 10575333, 10575334, 10575335, 10575336, 10575337, 10575338, 10575339, 10575340, 10575342, 10575343, 10575344, 10575345, 10592437, 10592438, 10592439, 10592440, 10592441, 10592442, 10592443, 10592444, 10592445, 10592446, 10592447, 10592448, 10592449, 10592450, 10592451, 10592452, 10592453, 10592454, 10592455, 10592456, 10592457, 10592458, 10592459
      • 0286: 10592355, 10592356, 10592357, 10592358, 10592359, 10592360, 10592361, 10592362, 10592363, 10592364, 10592365, 10592366, 10592367, 10592368, 10592369, 10592370, 10592371, 10592372, 10592373, 10592374, 10592385, 10592386, 10592387, 10592388, 10592389, 10592390, 10592391, 10592392, 10592393, 10592394, 10592395, 10592422, 10592423, 10592424, 10592425, 10592426, 10592427, 10592428, 10592429, 10592430, 10592431, 10592432, 10592433, 10592434, 10592435, 10592436, 10592473, 10592474, 10592475, 10592476, 10592477, 10592478, 10592482, 10592483, 10592484, 10592485, 10592486, 10592487, 10592488, 10592489, 10592490, 10592491, 10592492, 10592493, 10592494, 10592496, 10592497, 10592498, 10592499, 10592500, 10592501, 10592502, 10592503, 10592504, 10592505, 10592506, 10592507, 10592508,
      • 0289: 10575265, 10575266, 10575267, 10575268, 10575269, 10575270, 10575271, 10704319
    • Remove ...Copyright...(38)
      • 0294: 10878556
      • 0296: 10927060
      • 0299: 11054602, 11054652
      • 0301: 11124095, 11124096
      • 0304: 11170086, 11170087, 11170088, 11170089, 11170090, 11170091, 11170092, 11170093, 11170094, 11170095, 11170096, 11170097, 11170098, 11180281
      • 0305: 11237485, 11237775, 11244144
      • 0307: 11304829
      • 0308: 11335204
      • 0309: 11373102, 11382835
      • 0310: 11391771, 11417968
      • 0311: 11448151
      • 0312: 11466785
      • 0314: 11545600, 11545700
      • 0315: 11572850
      • 0405: 9880233, 9880236, 9880238, 9880239
    • Remove ...Crown Copyright Copyright...
      • 0403: 9824696
    • Remove Copyright -Copyright 2000 John Wiley & Sons, Ltd.
      • 0301: 11114061
    • Remove ...(Japanese Association of Intellectual Copyright #130,591)..
      • 0306: 11276498

  • Remove reference at the end ...[..] (188)
    • Remove ...[Diabetologia..] (27)
      • 0284: 10550410, 10550411, 10550412, 10550413, 10550414, 10550415, 10550416, 10550417, 10550418, 10550419, 10550420, 10550421, 10550422
      • 0416: 10525655, 10525656, 10525657, 10525658, 10525659, 10525660, 10525661, 10525662, 10525663, 10525664, 10525665, 10525667, 10525668, 10525669
    • Remove ...[See editorial..] (21)
      • 0285: 10570444
      • 0287: 10649252, 10649256
      • 0289: 10699887, 10699897, 10699901
      • 0290: 10738225
      • 0291: 10760754, 10760768
      • 0296: 10918173
      • 0310: 11391604
      • 0404: 9874457, 9874467, 9874472
      • 0412: 10391568, 10391573
      • 0413: 10430251, 10430265, 10440689
      • 0415: 10491525
      • 0416: 10506695
    • Remove ...[Editorial comment..] (7)
      • 0306: 11283830, 11283831, 11283832, 11283833, 11283834, 11283835, 11283836
    • Remove ...[Losek JD. Hypoglycemia and the ABC'S..]
      • 0286: 10613939
    • Remove ...[Originally published in..] (3)
      • 0306: 11276057, 11276063, 11276064
    • Remove ...[bj163]
      • 0287: 10629620
    • Remove ...[see text] (5)
      • 0290: 10753871
      • 0406: 10189255
      • 0407: 10052594, 10079941
      • 0413: 10438465
    • Remove ...[formula: see text] (7)
      • 0286: 10629949
      • 0291: 10782308
      • 0403: 9836450
      • 0412: 10399301
      • 0413: 10420594
      • 0416: 10515064, 10520260
    • Remove ...[figure: see text]
      • 0292: 10800657
    • Remove ...[not readable: see text] (2)
      • 0302: 11142883, 11142885
    • Remove ...[reaction: see text] (30)
      • 0314: 11556387
      • 0318: 11720544, 11720546, 11720548, 11720549, 11720552, 11720553, 11720554, 11720555, 11720556, 11720557, 11720558, 11720559, 11720560, 11720563, 11720564, 11720565, 11720566, 11720568, 11720569, 11720570, 11720571, 11720572, 11720575, 11720578, 11720579, 11720581, 11720582, 11720583, 11720584
    • Remove ...[structures: see text] (16)
      • 0295: 10907885
      • 0309: 11383903
      • 0315: 11566059
      • 0318: 11720545, 11720547, 11720550, 11720551, 11720561, 11720562, 11720567, 11720573, 11720574, 11720576, 11720577, 11720580, 11722558
    • Remove ...[structure: see text] (5)
      • 0298: 10998489
      • 0304: 11217974, 11217982
      • 0404: 9874236
      • 0412: 10408342
    • Remove ...[table: see text] (3)
      • 0303: 11190348
      • 0407: 10085619
      • 0412: 10410845
    • Remove ...[Table: see text]
      • 0319: 11753520
    • Remove ...[See accompanying article on pages..] (2)
      • 0305: 11241234, 11241235
    • Remove ...[ru5]
      • 0288: 10669549
    • Remove ...[The sequence data described in this paper have been submitted to..] (11)
      • 0288: 10673275
      • 0299: 11042149, 11042151, 11042155
      • 0397: 9647635, 9647637, 9647639
      • 0405: 9927484
      • 0412: 10413401, 10413403, 10413405
    • Remove ...[Primer sequences used in this study are available..]
      • 0291: 10779497
    • Remove ...[American Board of Emergency Medicine. Report of the Task Force on..]
      • 0291: 10783410
    • Remove ...[This abstract has been prepared centrally.] (4)
      • 0292: 10796470, 10796496, 10796629
      • 0303: 11034677
    • Remove ...[Worksheets with examplen calculations may be retrieved using anonymous ftp..]
      • 0293: 10841407
    • Remove ...[Lee SJ, Lee WE,..]
      • 0293: 10841921
    • Remove ...[See related article on page..]
      • 0296: 10951342
    • Remove ...[An appendix describing the molecular marker loci is available..]
      • 0299: 11042150
    • Remove ...[A table with the segregation data is available..]
      • 0299: 11042156
    • Remove ...[The quantitative trait loci described in this paper have been submitted..]
      • 0301: 11116089
    • Remove ...[Details of the SNPs and RFLP assays can be found..]
      • 0303: 11156626
    • Remove ...[Reprinted from J. Am. Chem..]
      • 0304: 11180641
    • Remove ...[Stiell IG, Lesiuk H, Wells GA,..]
      • 0312: 11468612
    • Remove ...[SAGE data are all available at..]
      • 0316: 11591645
    • Remove ...[interview by Mari N. Jensen]
      • 0317: 11684429
    • Remove ...[Expression data for the differentially expressed cDNAs are available..]
      • 0317: 11691851
    • Remove ...[Genetic markers polymorphic between the NOD and PWK strains are available..]
      • 0397: 9647636
    • Remove ...[The nucleotide sequence data reported in this paper are accessible..]
      • 0397: 9647641
    • Remove ...[Fold predictions for proteins from 14 proteomes are available..]
      • 0405: 9927481
    • Remove ...[Translations are provided in the International Abstracts..] (14)
      • 0407: 10052387, 10052388, 10052389, 10052390, 10052391, 10052392, 10052393
      • 0411: 10359215, 10359216, 10359217, 10359218, 10359219, 10359220, 10359221
    • Remove ...[The software is packaged as a Jar file available..]
      • 0407: 10085619
    • Remove ...[figure in text]
      • 0408: 10098901
    • Remove ...[American Board of Emergency Medicine:..]
      • 0409: 10216329
    • Remove ...[The data shown in Figure 3 are available..]
      • 0410: 10330129
    • Remove ...[J. McQuaid, B. Roebuck,..]
      • 0411: 10334822
    • Remove ...[S.T. Zalesak,..]
      • 0411: 10334823
    • Remove ...[R.K.S. Hankin, Heavy gas..]
      • 0411: 10334824
    • Remove ...[1996: Trends Cell Biol. 6:85-89]
      • 0413: 10423275
    • Remove ...[EHP 107:A196-A201 (April 1999)]
      • 0413: 10441319

  • Remove ...[Key words: (4)
    • 0290: 10751293
    • 0291: 10788860
    • 0295: 10888947
    • 0300: 11064527

  • Remove ABSTRACT related words (12)
    • Remove ...(ABSTRACT TRUNCATED) (7)
      • 0287: 10654982
      • 0300: 11074393
      • 0303: 11062606
      • 0304: 11158495
      • 0310: 11389298
      • 0411: 10368776
      • 0412: 10416202
    • Remove ...[abstract corrected] (2)
      • 0408: 10093604, 10093605
    • remove ...(abstract were not included)...
      • 0289: 10695616
    • remove ...(abstracts presented at recent scientific meetings, manufacturers' package inserts)...
      • 0306: 11261533
    • remove ...(abstract no. P2-615)...
      • 0314: 11530280

  • Remove ...[correction..]... (58)
    • 0284: 10560191, 10565149
    • 0285: 10581562, 10581576, 10582017
    • 0286: 10596229, 10602121, 10618746
    • 0287: 10643276, 10650528
    • 0289: 10693350, 10701356, 10703200, 10704319, 10709199, 10719439
    • 0290: 10726348, 10738752
    • 0291: 10756793, 10763107
    • 0293: 10852034, 10853250
    • 0295: 10896377
    • 0296: 10951341
    • 0297: 10974787
    • 0299: 11031442, 11031467, 11036826
    • 0308: 11326441
    • 0310: 11410162
    • 0311: 11424476
    • 0314: 11523172, 11533598
    • 0319: 11747174
    • 0402: 9811196
    • 0404: 9863116, 9866026, 9868076
    • 0406: 9974038
    • 0407: 10050546, 10077916
    • 0408: 10096200, 10096236, 10198769, 10202767, 10204260
    • 0409: 10224916
    • 0410: 10325603, 10330897, 10349448
    • 0412: 10394725, 10410516, 10414039
    • 0414: 10474860
    • 0415: 10485033, 10488620
    • 0416: 10512030, 10520287