Working on article, huge enhancements of some metrics

Author: PonteIneptique

.gitignore

@@ -7,8 +7,17 @@ dataset.py
 models/
 /*.tar
 /*.csv
+/bfmmss*.png
 
 
+*.~lock.*
+
+# LaTex
+
+*.gz
+*.out
+*.aux
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -34,6 +43,8 @@ wheels/
 *.egg-info/
 .installed.cfg
 *.egg
+
+# Pytho again
 MANIFEST
 
 # PyInstaller

article/accuracies.csv

@@ -1,51 +1,35 @@
-Epoch,CNN Train,CNN Dev,CNN No Pos,CNN No Pos Dev,CNN lower,CNN lower dev,CNN norm,CNN norm dev
-1,0.786266304752891,0.709142399576199,0.689777629626963,0.709214637218162,0.681192650156913,0.752291474725391,0.858956883185806,0.846770435411821
-2,0.785779466200953,0.861885154848725,0.542447293473553,0.551385123339482,0.818583115700758,0.874488747574775,0.868726099593356,0.867646844366021
-3,0.843381669377578,0.881942111044953,0.540089706909816,0.553920003378136,0.832318358536184,0.877288605134657,0.881975415371764,0.889957950384483
-4,0.739890542732449,0.863581882925702,0.601435069063638,0.661435262574253,0.824761081482988,0.70912843914533,0.896227734014953,0.900517212921705
-5,0.786118390201626,0.901634556611301,0.70915892545498,0.831812008031983,0.794786639061154,0.909913125414775,0.912246559618333,0.931269019008097
-6,0.842523506467222,0.913497908233096,0.659857671314353,0.868656695844457,0.839672959281418,0.934870686369474,0.939404587193545,0.938252913509043
-7,0.920165211422549,0.951469818475813,0.709129780844836,0.889241510735179,0.896089318648783,0.936796639986161,0.94227053109278,0.918177522546936
-8,0.933617679736798,0.928927454166348,0.824897235830216,0.885489713835699,0.878354505610043,0.94658310449375,0.834692065058121,0.929583857379773
-9,0.779168933281995,0.934301893072499,0.814076678504472,0.919837993647596,0.873256424319141,0.96571502747593,0.891117563062835,0.942802892524121
-10,0.745567960353223,0.908630678111061,0.754193077636844,0.889211517307864,0.813579360857846,0.85217343494484,0.846285401240207,0.936605311289894
-11,0.688252552801102,0.631077729583945,0.629655755556611,0.878224463083632,0.93211472428693,0.970494235765736,0.87442890140153,0.931245739184721
-12,0.69930127645539,0.920432489283456,0.731002741600474,0.88186009149573,0.899014883744961,0.957845961348321,0.941026690491221,0.953883345687314
-13,0.79447043158337,0.948859831433845,0.747966646157602,0.891088741553226,0.934133749424589,0.966564324168858,0.898929304215037,0.954790871691611
-14,0.682244185025798,0.844139318468888,0.725136487266843,0.88864992848702,0.937295746746958,0.960065617327307,0.899761277256794,0.949162346189527
-15,0.603712150405926,0.564464097927764,0.70187275801802,0.854253268130225,0.916357482904106,0.927165372217386,0.880593306302337,0.94796653181388
-16,0.617896196843206,0.776886051071866,0.627065957076136,0.869447803778606,0.879902266185922,0.946826887972697,0.915342979001773,0.946129532183912
-17,0.673640460532161,0.511818090274384,0.57056202596031,0.749456041681132,0.895235442086558,0.948872172546871,0.91052013088793,0.962007111966164
-18,0.536382712313148,0.609674434816477,0.542550203161979,0.599960815014603,0.904269486624707,0.956621301421829,0.932920801646176,0.952696190660291
-19,0.566915005334624,0.75968638772271,0.582336712276057,0.716696528709808,0.902596669275332,0.968938060949876,0.935121837301441,0.949996788230403
-20,0.619615520971264,0.798210246525453,0.540419037452739,0.562902111772077,0.927144765577795,0.965222827175652,0.894628811551734,0.939442243353706
-21,0.578853603279925,0.686186964292209,0.530989986725298,0.499729191876043,0.916789708152153,0.968379616347396,0.862962051529188,0.918159720299062
-22,0.591976046037398,0.763198002978769,0.530434841869317,0.497366812515594,0.903756490360848,0.939190536387845,0.892005398393072,0.95559621329574
-23,0.550027298476754,0.587394521473384,0.51190070852594,0.496549335941675,0.878300987396798,0.933389553757102,0.910469754810773,0.953471334592371
-24,0.550859082736791,0.573914292635461,0.542226766316207,0.729846400431897,0.835748041279673,0.939325949311351,0.922138720785568,0.953257196698199
-25,0.612122826440327,0.777179020051883,0.562799998002409,0.593270439455677,0.869303955777237,0.942448184121018,0.916800790016334,0.951609976301158
-26,0.583867769025443,0.667176888879937,0.548558639053616,0.552515453199981,0.86221669435527,0.938635275396888,0.898528064899527,0.948727476506678
-27,0.601287101806952,0.825336413731463,0.532295985478675,0.49951462179369,0.907055836783263,0.937018087279788,0.901657517139767,0.949472291950579
-28,0.602960415055229,0.764066409698554,0.529161994871221,0.498140520407963,0.910239010734583,0.950343554737644,0.916090664896568,0.951900213401613
-29,0.57504452131739,0.688375273133894,0.534448230031423,0.49779192623516,0.912922804796364,0.93713311608454,0.933584009384799,0.960107535343787
-30,0.577416724789965,0.747072557627065,0.530947872071492,0.497845298078996,0.877490334734666,0.943404893271632,0.929300706723803,0.955407421711715
-31,0.611596514664066,0.811146578773086,0.53601998651303,0.499492940300453,0.898054199724684,0.943157157293992,0.928437199796812,0.955881290200716
-32,0.613874948236508,0.77950611689464,0.537360627217123,0.499193246850107,0.886567920612341,0.948999667194935,0.924219094761535,0.957130855430385
-33,0.597312109298411,0.720152835193677,0.532556194661858,0.498349841385095,0.904977649308287,0.947279457489224,0.930789993321442,0.95845663370584
-34,0.577972357566426,0.717722395805701,0.527147842950653,0.497953582799081,0.909204262599813,0.949695042303312,0.932985325838599,0.956544154542408
-35,0.595741049196719,0.735063499612646,0.528026440974022,0.497664052032759,0.893619423927117,0.944878936754366,0.924705517737025,0.956259525985417
-36,0.586036688813446,0.695301498348011,0.524917448199545,0.497637231258384,0.87437218812485,0.943960902078143,0.91354251628573,0.955962200878391
-37,0.584768533215878,0.701688945941956,0.530873088805045,0.497723150739934,0.875373352321362,0.942170771047421,0.920195437964606,0.953253603331855
-38,0.592454893534853,0.698641096232235,0.530005149566366,0.497799570282481,0.878261896502048,0.945056486021324,0.894403035930348,0.950683994434015
-39,0.591984251140384,0.699285511497672,0.528691913742776,0.497990182724705,0.884160982611423,0.945589049788182,0.888115538178447,0.950648606452187
-40,0.594846243092863,0.707027301553236,0.52364438861976,0.498272515268394,0.874954627301186,0.94427462023417,0.87661818038194,0.946184489310305
-41,0.589211075050152,0.700218068899693,0.524828440220726,0.498340009159624,0.864047696088757,0.938561437434636,0.882043042019215,0.946468125582533
-42,0.584643984980074,0.68248945829556,0.527924029043415,0.498294299140443,0.855230111047658,0.937162749790515,0.873077539536213,0.943584848670946
-43,0.594517617309233,0.668755094755397,0.529670908729218,0.498467954917756,0.866195392358169,0.939241839959454,0.851430308399913,0.942993286009286
-44,0.589416170408076,0.665936610111491,0.528523064581949,0.498482346107117,0.858123328746907,0.939082336194658,0.858435687932456,0.942348420025884
-45,0.584564889905233,0.682794163759757,0.527942971265573,0.498468557802979,0.835937619330976,0.935290782842734,0.854141346478997,0.944974491013329
-46,0.589592319955025,0.689383774118791,0.526973199581468,0.498203221096935,0.839491791852932,0.93709936471858,0.880002595402253,0.946380578553106
-47,0.590061561806111,0.687192589947684,0.527829225856648,0.49824210250338,0.84433408184298,0.937014643314718,0.87524999151207,0.945762838491203
-48,0.586872437712653,0.68360893383358,0.529697183454258,0.498238549715395,0.846783146088237,0.936617481791456,0.88776438153093,0.949421530165446
-49,0.585611193063309,0.646407101172568,0.532597323550238,0.498666872141447,0.859824048407058,0.937861821513117,0.882910337823882,0.94861888025449
-50,0.584044353914895,0.65229933563433,0.535530328354714,0.498631482387396,0.861919800914635,0.941392135059635,0.888787299612995,0.950175937933965
+Epoch,CNN 1,CNN 2,CNN L,CNN L2,CNN w/o P,CNN N,CNN N 2,CNN L N,CNN L N 2,LSTM
+1,0.113865115473319,0.114842598051554,0.114195771601993,0.115835972718203,0.124521020683575,0.116527369560072,0.117429342790644,0.118438665735091,0.12033569284938,0.670462112879332
+2,0.046573883373152,0.046952832947328,0.047154250968127,0.046973550386671,0.052795819635434,0.047942750374486,0.048351091373045,0.048382771515501,0.048883984032243,0.668534556036643
+3,0.032694267109229,0.033033151428673,0.033280165905021,0.033360172860326,0.038818476028614,0.033720806391147,0.034038842824658,0.034184350584684,0.034354573703034,0.668378072623554
+4,0.026167214350533,0.026028367156286,0.026535042628588,0.026626830707364,0.031159712122058,0.026795169315774,0.02708861149642,0.027360685260013,0.027410148472623,0.668301192784179
+5,0.022008203308508,0.021994135071392,0.022488486767629,0.022683917405557,0.026208359567099,0.022613827432933,0.022897579075835,0.023170538136169,0.023339582982562,0.668256849272082
+6,0.019333275395343,0.019188345427759,0.019652754424256,0.019871564157376,0.022846316828775,0.019852554645879,0.020091619331483,0.020402554235748,0.020472278672618,0.66822136060947
+7,0.017191578073764,0.017174622671695,0.017636345444039,0.017785418009972,0.02025711226732,0.017702349902885,0.017976854370235,0.018332694952508,0.01830498856786,0.6681710468547
+8,0.015669044972837,0.015712366488998,0.016035391425753,0.016230992533413,0.018312343279831,0.016024948659686,0.016308253284692,0.016584884904732,0.01666422469114,0.668147657806964
+9,0.014462196761079,0.014294683938217,0.014831616148017,0.014970849858079,0.016752462491008,0.014812545204204,0.015090807492492,0.015456409141034,0.015448172509144,0.668118449522211
+10,0.013438037172303,0.01330412186394,0.013755708385421,0.013918037426764,0.01540361210404,0.013804012233179,0.014075514188161,0.014411296319643,0.01446253188623,0.668098743781558
+11,0.012614994064857,0.012388132844903,0.012907409961913,0.013092883495141,0.014325385593043,0.013042634371017,0.013200233379072,0.013567152115073,0.013424532527562,0.668066170005666
+12,0.011771994479459,0.011713160402408,0.012180195351373,0.012280231713345,0.013272779247436,0.012203698733701,0.012486865174958,0.012674308327806,0.012784990722253,0.668039920722751
+13,0.011200418432657,0.011081268179252,0.01155810675541,0.011789928899615,0.012566024011806,0.011771388267325,0.01185007607857,0.012110650314653,0.012181608975067,
+14,0.010673281670367,0.010509989099465,0.010956866740381,0.011073622622577,0.011777548090822,0.011125323825938,0.011269465597529,0.011554662297737,0.011558063195284,
+15,0.010155257868354,,0.010511980868521,0.010671981508129,0.011111998167427,0.010563416314357,0.010783351513197,0.01112991053508,0.01114224524391,
+16,0.009772817370016,,0.010126495669208,0.010249616529669,0.010586049911754,0.010161953321671,0.010339107201585,0.010276295343639,0.010683886237,
+17,0.009413273869357,,0.009674179078031,,0.010068297018136,0.009834481921024,0.009995451586674,0.009653073300594,0.010201461724811,
+18,,,0.009365777759049,,0.009601207305955,0.009462615105118,,0.009206381508441,0.009953611758449,
+19,,,0.009100519493314,,0.009212811686055,0.008768952755244,,0.008868569803463,0.00950575169014,
+20,,,,,0.008849915140144,,,0.008619247401446,0.009227716098966,
+21,,,,,0.008547240577846,,,0.008581858224226,0.008976117437202,
+22,,,,,0.008132688840701,,,,0.008787673159773,
+23,,,,,0.007695368266619,,,,0.008245814139646,
+24,,,,,0.007401325128144,,,,,
+25,,,,,0.007038912817985,,,,,
+26,,,,,0.00690626405045,,,,,
+27,,,,,0.006711490155905,,,,,
+28,,,,,0.00677519086028,,,,,
+29,,,,,0.006578997973513,,,,,
+30,,,,,0.006460488408301,,,,,
+31,,,,,0.006339392806851,,,,,
+32,,,,,0.006269767249287,,,,,
+33,,,,,0.006168832193151,,,,,
+34,,,,,0.006069372933942,,,,,

article/article.bib

@@ -118,6 +118,7 @@ @misc{jean_baptiste_camps_2019_2630574
   doi          = {10.5281/zenodo.2630574},
   url          = {https://doi.org/10.5281/zenodo.2630574}
 }
+
 @inproceedings{8269990,
 author={T. {Bluche} and S. {Hamel} and C. {Kermorvant} and J. {Puigcerver} and D. {Stutzmann} and A. H. {Toselli} and E. {Vidal}},
 booktitle={2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)},
@@ -130,3 +131,45 @@ @inproceedings{8269990
 doi={10.1109/ICDAR.2017.59},
 ISSN={2379-2140},
 month={Nov},}
+
+@misc{mufi,
+  title         = {{Medieval Unicode Font Initiative V4.0}},
+  author        = {Medieval Unicode Font Initiative},
+  year          = {2015},
+  month         = {dec},
+  handle        = {hdl.handle.net/1956/10699},
+}
+
+@misc{camps_pandora,
+  title        = {Pandora, A (language independent) Tagger Lemmatizer for Latin and the Vernacular},
+  author       = {Jean-Baptiste Camps, Thibault Clérice, Mike Kestemont, Enrique Manjavacas},
+  month        = nov,
+  year         = 2017,
+  url          = {https://www.academia.edu/35076560/Pandora_A_language_independent_Tagger_Lemmatizer_for_Latin_and_the_Vernacular},
+  howpublished = {{Atelier COSME}},
+}
+
+
+@misc{tnah_transcription,
+  editor       = {Ariane Pinche},
+  author       = {Master TNAH},
+  title        = {{Exercices TEI du master Technologies Numériques Appliquées à l'Histoire}},
+  year         = 2019,
+  url          = {https://github.com/Chartes-TNAH/digital-edition}
+}
+
+@misc{bfmmss,
+  author       = {Alexei Lavrentiev},
+  title        = {{Corpus BFMMSS}},
+  year         = 2019,
+  url          = {http://txm.bfm-corpus.org/}
+}
+
+@misc{thibault_clerice_2019_3237731,
+  author       = {Thibault Clérice},
+  title        = {PonteIneptique/mufidecode: v0.1.0},
+  month        = jun,
+  year         = 2019,
+  doi          = {10.5281/zenodo.3237731},
+  url          = {https://doi.org/10.5281/zenodo.3237731}
+}