RetroC2 temporal classification challenge

Guess the publication year of a Polish text.

# submitter when description dev-0 RMSE dev-1 RMSE test-A RMSE
67 [anonymised] 2019-05-22 08:38 BiLSTM 30epochs 22nd new tokenizer 69.7703224016867 45.6059264422252 50.3807109765053
99 [anonymised] 2019-05-22 08:36 BiLSTM 3- ep0 epochs 22nd new tokenizer 69.7703224016867 45.6059264422252 N/A
81 [anonymised] 2019-05-21 19:00 BiLSTM 3- epochs 22nd new tokenizer 69.7703224016867 45.6059264422252 62.4891168784141
14 Marcin Szczepański 2019-05-17 18:45 Vowpal Wabbit - linear regression + graph vowpal-wabbit graph 29.0918127745396 24.4450171910376 27.8076763284082
12 [anonymised] 2019-05-11 22:40 BiLSTM, 30epochs, model 28th 69.7703224016867 45.6059264422252 24.6046977976762
21 [anonymised] 2019-05-09 23:19 ready-made tf-df: a fix ready-made linear-regression tf-idf 29.8173795226618 26.2921271710746 33.3877305442333
11 [anonymised] 2019-05-09 17:51 BiLSTM, 30epochs, model 28th N/A 45.6059264422252 24.6046977976762
10 [anonymised] 2019-05-09 05:03 BiLSTM, 30epochs, model 28th N/A N/A 24.6046977976762
15 Yurkee 2019-05-06 15:08 tfidf 3k words low range 59.4457367071015 N/A 28.2773652793967
13 Yurkee 2019-05-06 15:05 tfidf 50k words low reduction range ready-made linear-regression tf-idf 59.4457367071015 N/A 27.7078389075627
51 [anonymised] 2019-05-06 15:01 My solution go.php rule-based 57.517490776426 45.1415486693373 42.6874502803664
46 Yurkee 2019-05-06 14:49 transfer files to VM 59.4457367071015 N/A 40.6743752013942
45 Yurkee 2019-05-06 14:08 all documents to predict on vector 30k words TFIDF KNN ready-made knn tf-idf 59.4457367071015 N/A 40.6743752013942
22 Yurkee 2019-05-06 13:57 all documents to predict on vector 10k words TFIDF Linear ready-made linear-regression tf-idf 59.4457367071015 N/A 34.4437965221145
58 Yurkee 2019-05-06 13:53 300 documents to predict on vector 10k words TFIDF Linear self-made linear-regression tf-idf 59.4457367071015 N/A 43.571311695525
9 [anonymised] 2019-05-03 19:49 BiLSTM w/o sorting N/A 43.7335557697024 23.2248476980084
18 Stanislaw-Golebiewski 2019-05-03 18:37 3000 words tf-idf self-made linear-regression tf-idf 34.2369685276312 30.8653827030961 32.631136288752
19 Stanislaw-Golebiewski 2019-05-03 17:25 2500 words tf-idf 34.8569785611239 31.5213112179354 32.9116638197651
20 Stanislaw-Golebiewski 2019-05-03 16:45 2000 words tf-idf self-made linear-regression tf-idf 35.6715165640611 32.11403240263 33.3838093993877
26 Stanislaw-Golebiewski 2019-05-03 16:27 1000 words tf-idf 38.9252990055191 35.2242332982084 36.0039460552677
8 [anonymised] 2019-05-03 07:17 BiLSTM w\o sorting N/A N/A 23.2248476980084
66 Yurkee 2019-04-29 14:57 self made TFIDF 1000 documents 500 word vector KNN4 self-made linear-regression knn tf-idf 59.4457367071015 N/A 48.3233936778994
35 Adrian Witczak 2019-04-28 20:08 linner ready tf ready-made linear-regression tf 51.5620887802236 41.3998474098027 39.2396476468827
65 Yurkee 2019-04-27 18:41 change encoding 59.4457367071015 N/A 47.0935417504352
64 Yurkee 2019-04-27 17:54 tfidf - not ready 59.4457367071015 N/A 47.0935417504352
1 Artur Nowakowski 2019-04-19 07:52 optimized word2vec + nn neural-network word2vec 15.9133276502658 14.5874603796497 17.7894648020368
6 Artur Nowakowski 2019-04-17 16:02 wordvec + nn 5-fold validation 17.6439352462756 16.8033092057152 20.2318542069896
5 Artur Nowakowski 2019-04-17 09:20 word2vec + nn optimized for dev1 18.7139956844749 15.8506510349661 19.9154520710084
78 [anonymised] 2019-04-16 22:30 Now with CHARTS self-made linear-regression graph 62.4955262147604 57.4777141790552 57.1188588829586
25 Maksym Krawczyk 2019-04-16 16:36 simple lin reg self-made linear-regression graph N/A N/A 35.9579583008407
34 Marcin Szczepański 2019-04-16 16:24 Figure add self-made linear-regression graph N/A 40.4788731431313 38.4307530115124
3 Artur Nowakowski 2019-04-16 16:13 basic word2vec + nn solution (optimized for dev0) 16.7930422327498 17.7020156432858 19.5574245198048
33 Stanislaw-Golebiewski 2019-04-16 15:36 years in text self-made linear-regression graph 50.7096731721368 N/A 38.4189161791553
92 Stanislaw-Golebiewski 2019-04-16 15:20 mean year found in text 1341469.0781636 N/A 1345919.11668638
38 PioBec 2019-04-16 13:24 Regresja liniowa (USA |usa |stany zjednoczone) + Lata linear-regression 48.5987838942367 42.9244459264943 39.382481157097
24 Maksym Krawczyk 2019-04-16 13:14 simple linear regression self-made linear-regression graph N/A N/A 35.9579583008407
37 PioBec 2019-04-16 13:10 Regresja liniowa (USA|usa|stany zjednoczone) plus lata N/A 42.9244459264943 39.382481157097
48 Adrian Witczak 2019-04-16 09:49 linear regression self-made linear-regression graph 61.4741987839098 40.2280331504805 41.2202128154632
63 Yurkee 2019-04-16 01:12 Merge branch 'master' of ssh://gonito.net/huntekah/retroc2 self-made linear-regression graph 59.4457367071015 N/A 47.0935417504352
62 Yurkee 2019-04-16 00:56 Honest one variable solution, without fancy, and thus easy methods self-made linear-regression graph 59.4457367071015 N/A 47.0935417504352
16 Gabi 2019-04-15 20:33 Basic ready-made solution with one column ready-made linear-regression tf-idf 30.2122311179054 26.6767681265913 28.2975786146497
53 [anonymised] 2019-04-15 18:40 excel plots :) self-made linear-regression graph 52.0918841002776 46.7960517353929 42.9909381854081
43 [anonymised] 2019-04-15 18:39 XXDDDD my solution self-made linear-regresion ADD CHARTS selfMadeLinearRegres_Solver.py self-made linear-regression graph 48.6992588956004 42.9275641290162 39.9041796720734
44 mario 2019-04-15 16:35 one variable regression self-made linear-regression graph N/A N/A 40.2193255080054
52 [anonymised] 2019-04-15 12:46 hope that is final one self-made linear-regression 52.0918841002776 46.7960517353929 42.9909381854081
98 [anonymised] 2019-04-15 12:40 now more iterations 52.0918841002776 46.7960517353929 N/A
90 [anonymised] 2019-04-15 12:02 forgot to add out files xd 279.732575385688 285.867717752554 269.459884639896
91 [anonymised] 2019-04-15 11:57 date detection and linear regression 271.214678425392 296.532525550574 271.270419431417
42 [anonymised] 2019-04-15 11:54 XDDD my solution self-made linear-regresion selfMadeLinearRegres_Solver.py self-made linear-regression 48.6992588956004 42.9275641290162 39.9041796720734
7 Artur Nowakowski 2019-04-15 11:40 Linear regression with TF-IDF weighing scheme ready-made linear-regression tf-idf 20.7499143486405 20.6760099243222 22.341234282235
17 Gabi 2019-04-11 18:56 Basic ready-made solution ready-made linear-regression tf-idf 30.7234607365907 26.9628102276184 28.66834232094
36 PioBec 2019-04-10 10:28 wykrywanie dat top prio rule-based 48.2379844527658 41.7546355576506 39.2463950791307
97 Joanna 2019-04-09 20:20 solution with scikit regression N/A N/A N/A
96 [anonymised] 2019-04-09 19:11 not many rules rule-based N/A N/A N/A
75 Stanislaw-Golebiewski 2019-04-09 16:55 post OCR signs 69.841140844155 N/A 55.4003191941823
74 Stanislaw-Golebiewski 2019-04-09 16:53 post OCR signs 73.2362774868387 N/A 55.4003191941823
88 Stanislaw-Golebiewski 2019-04-09 16:51 post OCR signs 73.2362774868387 N/A 69.969609393827
87 Stanislaw-Golebiewski 2019-04-09 16:46 post OCR signs 351.237129470242 N/A 69.969609393827
77 Joanna 2019-04-09 16:43 solution with simple word list2 rule-based 63.5234179556198 55.1719716851188 56.1242305171368
85 Stanislaw-Golebiewski 2019-04-09 16:28 post OCR signs N/A N/A 66.0462703769767
50 [anonymised] 2019-04-09 16:15 My solution basic rule-based solver.py rule-based 57.517490776426 45.1415486693373 42.6823953611153
49 Marcin Szczepański 2019-04-09 16:12 fourth solution rule-based N/A 43.9473525079626 41.2351085725362
29 Maksym Krawczyk 2019-04-09 15:28 bad solution 2 rule-based N/A N/A 37.1970815130988
80 Maksym Krawczyk 2019-04-09 13:07 Bad rule-based solution rule-based N/A N/A 59.7481947316983
32 [anonymised] 2019-04-08 21:02 better stupid solution rule-based 50.2288496863145 39.7726727210278 38.368116744008
31 [anonymised] 2019-04-08 19:59 stupid solution rule-based 50.2341209498185 41.6827039281627 38.1771946193023
47 [anonymised] 2019-04-08 18:10 my very simple solution3 rule-based 50.6066623616284 44.0781603910467 40.8376241083043
40 mario 2019-04-08 15:24 rulebased rule-based N/A N/A 39.7811993808485
56 Yurkee 2019-04-08 15:23 all rules rule-based 54.0642657278922 N/A 43.1007685372352
55 Yurkee 2019-04-08 15:21 slowa 57.733131454545 N/A 43.1007685372352
39 Olga Kwaśniewska 2019-04-08 12:54 Based on a list with years rule-based 48.665808787664 43.0312082090479 39.6946705477268
95 Olga Kwaśniewska 2019-04-08 12:42 Improve guessing accuracy for de0 dev1 48.665808787664 43.0312082090479 N/A
76 [anonymised] 2019-04-08 11:32 my very simple solution2A 63.4110714614002 49.9009067523053 55.5831831486368
94 [anonymised] 2019-04-07 22:13 my very simple solution1 63.4110714614002 49.9009067523053 N/A
54 Yurkee 2019-04-07 19:51 complicated rules make Good/Bad results 57.733131454545 N/A 43.1007685372352
79 Mateusz Hinc 2019-04-07 18:17 most popular words in 10-year periods java rule-based 51.1174365828326 54.0801339594419 57.980900088857
68 Yurkee 2019-04-07 09:44 simple rule based rule-based 57.733131454545 N/A 52.3055783029432
84 [anonymised] 2019-04-07 08:42 my best solution rule-based 86.440702205017 61.2803320371466 65.9525177438093
57 [anonymised] 2019-04-06 16:59 based on historical word list rule-based 57.2198976020558 46.2865487391857 43.4243900255141
41 Gabi 2019-04-05 19:22 simple set solution rule-based 53.9327223201846 37.2452323472672 39.8851100216834
28 Artur Nowakowski 2019-04-03 11:52 simple solution rule-based 50.2546167620924 37.5955361225008 36.5632022665678
73 [anonymised] 2019-04-02 16:50 LSTM EPOCHS=10 LR=0.001 DROPOUT=0.1 - input w/o filtering, adding missing line neural-network bilstm 66.3481683975627 N/A 55.114709507032
83 [anonymised] 2019-03-30 19:01 LSTM EPOCHS=10 LR=0.001 DROPOUT=0.2 - input w/o filtering, adding missing line neural-network bilstm 73.2270955593451 N/A 63.9134662864477
89 [anonymised] 2019-03-27 17:36 LSTM EPOCHS=10 LR=0.001 DROPOUT=0.5 - input w/o filtering, adding missing line neural-network bilstm N/A N/A 97.9024820621187
72 [anonymised] 2019-02-19 09:08 Modyfikacja skryptu do uruchomienia 72.5293605068765 N/A 52.9502612058947
71 [anonymised] 2019-02-19 08:50 5 epochs; filtered input; feedforward network neural-network 72.5293605068765 N/A 52.9502612058947
82 p/tlen 2018-08-30 20:16 tescik 5 stupid N/A N/A 62.5015854401984
86 p/tlen 2018-08-30 19:38 tescik 3 stupid N/A N/A 69.5973172149601
60 p/tlen 2018-08-30 19:31 tescik2 stupid N/A N/A 46.512637724839
61 p/tlen 2018-08-30 19:27 test stupid N/A N/A 46.5906817939381
70 [anonymised] 2018-08-14 18:29 dev0 first solution stupid neural-network 57.8633606139503 N/A 52.7210444434977
27 p/tlen 2018-05-29 07:19 try xgboost xgboost 39.9068228142474 37.2279801383082 36.4836152503447
4 p/tlen 2017-07-08 12:52 VW with yearly resolution 23.0653690364102 17.1779858695333 19.6954795180452
93 p/tlen 2017-07-08 12:50 VW with yearly resolution N/A N/A N/A
23 p/tlen 2017-07-07 10:23 year references combined with hand-crafted rules 42.3022587251256 42.6540785469616 35.806650092557
59 p/tlen 2017-07-07 09:41 hand-crafted rules 48.6015472449078 50.6464292298094 44.1672440144163
30 p/tlen 2017-07-07 09:11 year references 46.4473742694431 39.8086062658875 37.6519061214151
2 p/tlen 2017-05-31 04:49 VW -nn 6 on up to 4-grams and [5-7] tokens vowpal-wabbit neural-network 22.4132853145918 16.9906594140501 19.5014391655249
69 p/tlen 2017-05-26 21:48 null model stupid null-model 57.7353219856082 51.9064932230693 52.5394894247378