Problem while making ann file

Help
Prakash
2011-10-11
2013-04-26
  • Prakash
    Prakash
    2011-10-11

    while making ann file such problem appears, do anybody have answer for it.

    dinf@dinf-775Dual-880Pro:~/informationextraction/minorthird_20080611$ java -Xmx900m edu.cmu.minorthird.ui.TrainExtractor -learner "Recommended.CRFAnnotatorLearner()" -output person -labels "/home/dinf/informationextraction/Document/Tag/" -saveAs "/home/dinf/informationextraction/TrainExtractor/person.ann" -spanType person
    *** Minorthird: Version 13.7.10.8 ***
    option: learner=Recommended.CRFAnnotatorLearner()
    option: output=person
    option: labels=/home/dinf/informationextraction/Document/Tag/
    The script name is: /home/dinf/informationextraction/Document/Tag/
    option: saveAs=/home/dinf/informationextraction/TrainExtractor/person.ann
    option: spanType=person
    Task presenting examples to AnnotatorLearner: 1 document(s) in 1.33 sec
    Task presenting examples to AnnotatorLearner: 7 document(s) in 2.40 sec
    Task presenting examples to AnnotatorLearner: 13 document(s) in 3.54 sec
    Task presenting examples to AnnotatorLearner: 16 document(s) in 4.55 sec
    Task presenting examples to AnnotatorLearner: 19 document(s) in 5.98 sec
    Task presenting examples to AnnotatorLearner: 22 document(s) in 7.39 sec
    Task presenting examples to AnnotatorLearner: 25 document(s) in 8.89 sec
    Task presenting examples to AnnotatorLearner: 28 document(s) in 10.57 sec
    Task presenting examples to AnnotatorLearner: 31 document(s) in 11.76 sec
    Task presenting examples to AnnotatorLearner: 35 document(s) in 12.95 sec
    Task presenting examples to AnnotatorLearner: 39 document(s) in 14.35 sec
    Task presenting examples to AnnotatorLearner: 43 document(s) in 15.41 sec
    Task presenting examples to AnnotatorLearner: 46 document(s) in 16.53 sec
    Task presenting examples to AnnotatorLearner: 50 document(s) in 17.54 sec
    Task presenting examples to AnnotatorLearner: 54 document(s) in 18.87 sec
    Task presenting examples to AnnotatorLearner: 60 document(s) in 20.04 sec
    Task presenting examples to AnnotatorLearner: 66 document(s) in 21.63 sec
    Task presenting examples to AnnotatorLearner: 71 document(s) in 22.81 sec
    Task presenting examples to AnnotatorLearner: 76 document(s) in 24.03 sec
    Task presenting examples to AnnotatorLearner: 81 document(s) in 25.07 sec
    Task presenting examples to AnnotatorLearner: 89 document(s) in 26.15 sec
    Task presenting examples to AnnotatorLearner: 94 document(s) in 27.26 sec
    Task presenting examples to AnnotatorLearner: 99 document(s) in 28.31 sec
    Property: ll
    Number of features :41159
    Iteration 0 log-likelihood -221363.6999135608 norm(grad logli) 259366.48773292772 norm(x) 0.0
    Iteration 1 log-likelihood -46134.22191232311 norm(grad logli) 81022.79470161546 norm(x) 0.9999999999997993
    Iteration 2 log-likelihood -19954.105669845412 norm(grad logli) 31895.711915185242 norm(x) 1.4621373186638587
    Iteration 3 log-likelihood -12090.94946920915 norm(grad logli) 14325.943696071758 norm(x) 1.7707673729871714
    Iteration 4 log-likelihood -9130.524616091881 norm(grad logli) 6286.456455219789 norm(x) 2.033762624131078
    Iteration 5 log-likelihood -7968.652329495179 norm(grad logli) 3018.032878366158 norm(x) 2.2511218972668474
    Iteration 6 log-likelihood -7205.536750330857 norm(grad logli) 2139.849270827699 norm(x) 2.473268623838201
    Iteration 7 log-likelihood -5983.760693035052 norm(grad logli) 2332.667028176515 norm(x) 2.9378096745887827
    Iteration 8 log-likelihood -3556.749334271004 norm(grad logli) 1048.6633699899899 norm(x) 4.6229117067171765
    Iteration 9 log-likelihood -2676.71106751086 norm(grad logli) 693.0199913742323 norm(x) 5.843547155692945
    Iteration 10 log-likelihood -1992.6404993405088 norm(grad logli) 1268.4226641157627 norm(x) 7.350042006601476
    Iteration 11 log-likelihood -1597.0928931234484 norm(grad logli) 839.4328929630279 norm(x) 8.29359740592226
    Iteration 12 log-likelihood -1335.4930514348848 norm(grad logli) 374.4646542521216 norm(x) 9.01538134310517
    Iteration 13 log-likelihood -1140.1927871689395 norm(grad logli) 240.02050274252417 norm(x) 10.092742384910899
    Iteration 14 log-likelihood -969.1943489007087 norm(grad logli) 360.7399275237062 norm(x) 11.392499459930074
    Iteration 15 log-likelihood -816.2194413230328 norm(grad logli) 322.70358808556773 norm(x) 13.372580073293408
    Iteration 16 log-likelihood -686.099662099559 norm(grad logli) 342.4476201314477 norm(x) 17.036934456541623
    Iteration 17 log-likelihood -649.0335552996999 norm(grad logli) 138.6306086072713 norm(x) 16.006988347153523
    Iteration 18 log-likelihood -628.1365655838305 norm(grad logli) 140.066291459993 norm(x) 16.427946373439095
    Iteration 19 log-likelihood -552.9645308643654 norm(grad logli) 382.67078686227285 norm(x) 19.36270395509444
    Iteration 20 log-likelihood -490.2060075585008 norm(grad logli) 154.10575114978468 norm(x) 19.653366026321052
    Iteration 21 log-likelihood -440.14782124086554 norm(grad logli) 130.98800590360528 norm(x) 21.07243160530473
    Iteration 22 log-likelihood -380.992938542439 norm(grad logli) 73.64907753261745 norm(x) 21.880117597152495
    Iteration 23 log-likelihood -342.73683764675417 norm(grad logli) 79.64061551762354 norm(x) 22.897528517908523
    Iteration 24 log-likelihood -292.022797500194 norm(grad logli) 153.07375477208197 norm(x) 24.227522018343432
    Iteration 25 log-likelihood -270.45507070801307 norm(grad logli) 86.28473478867905 norm(x) 24.553063341223652
    Iteration 26 log-likelihood -256.2922546244947 norm(grad logli) 73.26865645974935 norm(x) 24.608668210334063
    Iteration 27 log-likelihood -229.6560975103638 norm(grad logli) 68.98347829040316 norm(x) 25.091778907692632
    Iteration 28 log-likelihood -209.48480493045977 norm(grad logli) 108.59498102801513 norm(x) 25.6550529036491
    Iteration 29 log-likelihood -193.18400801804086 norm(grad logli) 71.40512848304084 norm(x) 26.000281896430124
    Iteration 30 log-likelihood -173.28388154339336 norm(grad logli) 55.87791608925531 norm(x) 26.682989621484968
    Iteration 31 log-likelihood -162.78625032236675 norm(grad logli) 52.568429771847505 norm(x) 27.5259009952074
    Iteration 32 log-likelihood -1947.8070121183932 norm(grad logli) 22692.324348525963 norm(x) 28.107267910926694
    Iteration 33 log-likelihood -162.52112573081564 norm(grad logli) 51.804125174337145 norm(x) 27.53033585182911
    Iteration 34 log-likelihood -158.3833326580318 norm(grad logli) 346.710609420015 norm(x) 27.73502936536952
    Iteration 35 log-likelihood -158.4980078702027 norm(grad logli) 46.032959155738496 norm(x) 27.62061151801856
    Iteration 36 log-likelihood -149.63681587690314 norm(grad logli) 46.695706933651444 norm(x) 27.55947500528002
    Iteration 37 log-likelihood -140.60001378429902 norm(grad logli) 145.1188040923249 norm(x) 28.389946340502487
    Iteration 38 log-likelihood -133.88908876218045 norm(grad logli) 71.6881791767675 norm(x) 28.684135154959346
    Iteration 39 log-likelihood -1184.3772895142536 norm(grad logli) 22404.51668061944 norm(x) 29.22392443181691
    Iteration 40 log-likelihood -133.84055991094334 norm(grad logli) 71.07859462148078 norm(x) 28.686860004861295
    Iteration 41 log-likelihood -434.92689505869237 norm(grad logli) 21820.54190821964 norm(x) 29.03983709943701
    Iteration 42 log-likelihood -132.60461973942398 norm(grad logli) 62.591676067894966 norm(x) 28.76283977957203
    Iteration 43 log-likelihood -123.24492974351512 norm(grad logli) 63.53127637318972 norm(x) 29.264214051388677
    Iteration 44 log-likelihood -119.84079151446537 norm(grad logli) 92.04621319545699 norm(x) 29.68552968803872
    Iteration 45 log-likelihood -115.95429428142288 norm(grad logli) 51.08359507944407 norm(x) 30.75113318124974
    Iteration 46 log-likelihood -109.86038035729314 norm(grad logli) 30.97892263392301 norm(x) 30.60192239183401
    Iteration 47 log-likelihood -104.33630577197391 norm(grad logli) 23.60632630881156 norm(x) 30.7856953159415
    Iteration 48 log-likelihood -93.40352980664633 norm(grad logli) 29.239944218094593 norm(x) 31.945498023406724
    Iteration 49 log-likelihood -91.54296999321237 norm(grad logli) 104.81869166996441 norm(x) 34.15698299232759
    Iteration 50 log-likelihood -83.21913324204458 norm(grad logli) 22.960593787980606 norm(x) 33.897136870143996
    Iteration 51 log-likelihood -81.45118710443357 norm(grad logli) 20.231674519398823 norm(x) 34.26112943397394
    Iteration 52 log-likelihood -77.99429678143449 norm(grad logli) 21.725283620299894 norm(x) 35.094960927120965
    Iteration 53 log-likelihood -80.04797227396946 norm(grad logli) 118.73436112564204 norm(x) 36.91224898069139
    Iteration 54 log-likelihood -76.44713580732818 norm(grad logli) 49.42187370097082 norm(x) 35.812004497151285
    Iteration 55 log-likelihood -74.20670894936788 norm(grad logli) 27.334416246533298 norm(x) 36.245031099253424
    Iteration 56 log-likelihood -71.81520400351742 norm(grad logli) 34.315680590828 norm(x) 36.810012108754336
    Iteration 57 log-likelihood -69.7652194324433 norm(grad logli) 33.43397281415316 norm(x) 37.40050089617587
    Iteration 58 log-likelihood -68.3778004709302 norm(grad logli) 26.172574932611578 norm(x) 37.57050787452295
    Iteration 59 log-likelihood -64.82064835682937 norm(grad logli) 17.136102086101243 norm(x) 38.34425235878231
    Iteration 60 log-likelihood -63.76974741101192 norm(grad logli) 17.375690028043078 norm(x) 38.78449183160678
    Iteration 61 log-likelihood -61.88472389557107 norm(grad logli) 31.01558928539691 norm(x) 39.981211108349775
    Iteration 62 log-likelihood -61.51564021602699 norm(grad logli) 18.388395016693163 norm(x) 40.26164649517037
    Iteration 63 log-likelihood -60.47520624586836 norm(grad logli) 10.823935416088602 norm(x) 40.490872438882974
    Iteration 64 log-likelihood -59.681478679029574 norm(grad logli) 10.466834262865422 norm(x) 40.93300779005856
    Iteration 65 log-likelihood -58.5154850154348 norm(grad logli) 15.019689483883676 norm(x) 41.54500028586365
    Iteration 66 log-likelihood -59.13855651581827 norm(grad logli) 46.38108962729554 norm(x) 42.82255566143045
    Iteration 67 log-likelihood -58.139737867874956 norm(grad logli) 10.4263484418546 norm(x) 41.9458470867612
    Iteration 68 log-likelihood -57.99471570172941 norm(grad logli) 13.740242454200663 norm(x) 43.25072954357467
    Iteration 69 log-likelihood -58.51385801512295 norm(grad logli) 16.238277931455084 norm(x) 45.11285619919916
    Iteration 70 log-likelihood -57.67078437646487 norm(grad logli) 11.727172117598746 norm(x) 43.759879236601165
    Iteration 71 log-likelihood -57.77106954542132 norm(grad logli) 11.595276963740453 norm(x) 45.051644787430405
    Iteration 72 log-likelihood -57.55365241394664 norm(grad logli) 11.10786163170823 norm(x) 44.07507094973642
    Iteration 73 log-likelihood -58.98536552085953 norm(grad logli) 14.22730942988613 norm(x) 47.28282783960576
    Iteration 74 log-likelihood -57.31079260225976 norm(grad logli) 10.49682375993067 norm(x) 44.78156785016328
    Iteration 75 log-likelihood -102.58733613725045 norm(grad logli) 234.88213911779093 norm(x) 50.346952226815716
    Iteration 76 log-likelihood -57.76345941581424 norm(grad logli) 19.659158255137385 norm(x) 45.361808418302715
    Iteration 77 log-likelihood -57.329395412766274 norm(grad logli) 10.14454753209688 norm(x) 44.8865624040322
    Iteration 78 log-likelihood -57.31225485676765 norm(grad logli) 10.227755701939184 norm(x) 44.80253893453505
    Iteration 79 log-likelihood -57.31146289101796 norm(grad logli) 10.378265066041326 norm(x) 44.78589569329261
    Iteration 80 log-likelihood -57.31087990879454 norm(grad logli) 10.38308148273892 norm(x) 44.78242306959375
    Iteration 81 log-likelihood -57.310953912050124 norm(grad logli) 10.465675321466012 norm(x) 44.781740962452105
    Iteration 82 log-likelihood -57.310829340383194 norm(grad logli) 10.478108373730501 norm(x) 44.781593185679945
    Iteration 83 log-likelihood -57.31079964694701 norm(grad logli) 10.492374476130747 norm(x) 44.78157102631404
    Iteration 84 log-likelihood -57.31080188330407 norm(grad logli) 10.492669887201144 norm(x) 44.781568178732876
    Iteration 85 log-likelihood -57.31079264204615 norm(grad logli) 10.496922664695424 norm(x) 44.781567855149234
    Iteration 86 log-likelihood -57.31079264876333 norm(grad logli) 10.49682538334375 norm(x) 44.78156785038841
    Iteration 87 log-likelihood -57.310792630840396 norm(grad logli) 10.496822894683945 norm(x) 44.78156785016378
    Iteration 88 log-likelihood -57.31079260225976 norm(grad logli) 10.49682375993067 norm(x) 44.78156785016328
    Iteration 89 log-likelihood -57.31079260225976 norm(grad logli) 10.49682375993067 norm(x) 44.78156785016328
    Iteration 90 log-likelihood -57.31079259195758 norm(grad logli) 10.496823338184287 norm(x) 44.78156785016352
    Iteration 91 log-likelihood -57.31079259195758 norm(grad logli) 10.496823338184287 norm(x) 44.78156785016352
    Iteration 92 log-likelihood -57.31079259195758 norm(grad logli) 10.496823338184287 norm(x) 44.78156785016352
    Iteration 93 log-likelihood -57.3107926375215 norm(grad logli) 10.496823268648521 norm(x) 44.78156785016364
    Iteration 94 log-likelihood -57.31079259195758 norm(grad logli) 10.496823338184287 norm(x) 44.78156785016352
    CRF: lbfgs failed.
    Line search failed. See documentation of routine mcsrch. Error return of line search: info = 3 Possible causes: function or gradient are incorrect, or incorrect tolerances. (iflag == -1)
    Possible reasons could be:
    1. Bug in the feature generation or data handling code
    2. Not enough features to make observed feature value==expected value

     
  • Frank Lin
    Frank Lin
    2011-10-11

    If you've successfully created the specified .ann file, you can ignore the error warning.

    Often it just telling you that your training data is too small.