Sane words challenge
Guess if a given word is a correct Polish word in a given domain. Additionally, you have the information on reported frequency of the word in source texts. [ver. 1.0.0]
This is a long list of all submissions, if you want to see only the best, click leaderboard.
# | submitter | when | ver. | description | dev-0 F2.0 | test-A F2.0 | |
---|---|---|---|---|---|---|---|
100 | [anonymized] | 2020-01-27 13:02 | 1.0.0 | 16 neurons and 1 layer lr python linear-regression | 0.25038 | 0.22124 | |
98 | [anonymized] | 2019-12-17 16:52 | 1.0.0 | dlugosci+ fixed python linear-regression | 0.25065 | 0.22367 | |
82 | [anonymized] | 2019-12-04 21:56 | 1.0.0 | the best so far python pytorch-nn | 0.30188 | 0.29350 | |
78 | [anonymized] | 2019-12-04 19:29 | 1.0.0 | pytorch-nn more iterations python pytorch-nn | 0.35172 | 0.33117 | |
106 | [anonymized] | 2019-12-04 10:09 | 1.0.0 | dev-0 update python neural-network pytorch-nn | 0.14078 | 0.21551 | |
105 | [anonymized] | 2019-12-04 09:58 | 1.0.0 | dev-0 update | 0.00000 | 0.21551 | |
104 | [anonymized] | 2019-12-04 09:44 | 1.0.0 | ff network with tanh activation, batch size = 32 with 5000 epochs neural-network pytorch-nn | N/A | 0.21551 | |
76 | [anonymized] | 2019-12-04 09:02 | 1.0.0 | torch-nn python pytorch-nn | 0.32339 | 0.33287 | |
99 | [anonymized] | 2019-12-04 08:58 | 1.0.0 | fasttext + nn python pytorch-nn | 0.19271 | 0.22230 | |
84 | [anonymized] | 2019-12-04 08:28 | 1.0.0 | Pytorch nn, minibatch, improved previous solution python pytorch-nn | 0.27727 | 0.28049 | |
90 | [anonymized] | 2019-12-04 08:16 | 1.0.0 | Pytorch nn, minibatch, improved previous solution python pytorch-nn | 0.26027 | 0.24894 | |
89 | [anonymized] | 2019-12-04 00:50 | 1.0.0 | NN pytorch python pytorch-nn | 0.25732 | 0.25147 | |
97 | [anonymized] | 2019-12-04 00:08 | 1.0.0 | sane_words_torch_nn_onehot python pytorch-nn | 0.23461 | 0.22573 | |
119 | [anonymized] | 2019-12-03 23:39 | 1.0.0 | Attempt #3 | 0.16253 | 0.10073 | |
108 | [anonymized] | 2019-12-03 23:24 | 1.0.0 | test4 python pytorch-nn | 0.20663 | 0.20459 | |
118 | [anonymized] | 2019-12-03 22:16 | 1.0.0 | test | 0.09896 | 0.10610 | |
73 | Artur Nowakowski | 2019-12-03 21:43 | 1.0.0 | PyTorch simple NN python pytorch-nn | 0.33812 | 0.33842 | |
83 | [anonymized] | 2019-12-03 20:31 | 1.0.0 | pytorch neural network second solution python pytorch-nn | 0.30982 | 0.29079 | |
111 | [anonymized] | 2019-12-03 17:01 | 1.0.0 | Test for nn python pytorch-nn | 0.17521 | 0.18517 | |
101 | [anonymized] | 2019-12-03 14:08 | 1.0.0 | Improve results python linear-regression | 0.21041 | 0.21882 | |
115 | [anonymized] | 2019-12-01 00:47 | 1.0.0 | fixed regression python linear-regression | 0.16082 | 0.15625 | |
88 | [anonymized] | 2019-11-30 19:50 | 1.0.0 | very simple solution with torch.nn python pytorch-nn | 0.27827 | 0.25664 | |
16 | [anonymized] | 2019-11-30 18:59 | 1.0.0 | Neural net 512x256 one hot word python pytorch-nn | 0.47321 | 0.44029 | |
113 | [anonymized] | 2019-11-29 13:57 | 1.0.0 | Sane words, with score python linear-regression | 0.18430 | 0.17401 | |
112 | [anonymized] | 2019-11-29 13:29 | 1.0.0 | Sane words, early stopping python linear-regression | 0.18712 | 0.18134 | |
79 | [anonymized] | 2019-11-27 18:11 | 1.0.0 | Simple nn solution with torch (stupid params???) python pytorch-nn | 0.34200 | 0.32922 | |
125 | [anonymized] | 2019-11-27 10:22 | 1.0.0 | dlugosci+ python linear-regression | 0.16112 | N/A | |
86 | [anonymized] | 2019-11-27 09:35 | 1.0.0 | solution python linear-regression | 0.29004 | 0.26632 | |
94 | [anonymized] | 2019-11-27 07:49 | 1.0.0 | solution 16N python linear-regression | 0.27095 | 0.24304 | |
96 | [anonymized] | 2019-11-27 06:45 | 1.0.0 | LR with 16 neurons python linear-regression | 0.26102 | 0.23550 | |
91 | [anonymized] | 2019-11-27 06:23 | 1.0.0 | My solution python linear-regression | 0.24028 | 0.24635 | |
116 | [anonymized] | 2019-11-27 01:10 | 1.0.0 | NN 16 python linear-regression | 0.16082 | 0.15624 | |
93 | [anonymized] | 2019-11-26 21:36 | 1.0.0 | logistic regresion python linear-regression | 0.27123 | 0.24328 | |
95 | [anonymized] | 2019-11-26 21:13 | 1.0.0 | Neural network python linear-regression | 0.25245 | 0.23634 | |
92 | [anonymized] | 2019-11-26 13:15 | 1.0.0 | Neural net 1 hidden layer 16 neurons python linear-regression | 0.27130 | 0.24335 | |
87 | [anonymized] | 2019-11-22 02:02 | 1.0.0 | 32x32 selfmade NN pytorch alpha -1.5 420k loop python linear-regression | 0.27660 | 0.26247 | |
107 | [anonymized] | 2019-11-21 20:40 | 1.0.0 | slightly better nn python linear-regression | 0.21801 | 0.21084 | |
114 | [anonymized] | 2019-11-21 20:00 | 1.0.0 | simple nn with silly function on words python linear-regression | 0.16670 | 0.16175 | |
64 | p/tlen | 2018-05-22 11:44 | 1.0.0 | adaboost, f-measure on train=0.4200 | 0.37069 | 0.36488 | |
85 | p/tlen | 2018-05-22 09:28 | 1.0.0 | decision tree, classes balanced, f-measure on train=0.9985 decision-tree | 0.24223 | 0.26697 | |
74 | p/tlen | 2018-05-22 09:15 | 1.0.0 | decision tree, classes balanced, f-measure on train=0.4610 scikit-learn decision-tree | 0.33214 | 0.33503 | |
75 | p/tlen | 2018-05-22 07:48 | 1.0.0 | random forest, n_estimators=100, max_depth=4, oob_score, f-measure on train=0.3805 scikit-learn random-forest | 0.34976 | 0.33436 | |
81 | p/tlen | 2018-05-22 07:34 | 1.0.0 | RandomForest, n_estimators=5, classes balanced, f-measure on train=0.3884 scikit-learn random-forest | 0.31619 | 0.29907 | |
62 | p/tlen | 2018-05-22 07:27 | 1.0.0 | bagging, oob_score, classes balanced, n_estimators=5, f-measure on train=0.5268 scikit-learn bagging | 0.37227 | 0.37147 | |
70 | p/tlen | 2018-05-22 07:19 | 1.0.0 | bagging, class balanced, n_estimators=5, max_depth=10, f-measure on train=0.5237 bagging | 0.36852 | 0.34739 | |
120 | p/tlen | 2018-05-22 07:12 | 1.0.0 | bagging, n_estimators=20, f-measure on train=0.1891 | 0.07812 | 0.08035 | |
121 | p/tlen | 2018-05-22 06:52 | 1.0.0 | bagging with 5 estimators, f-measure on train=0.2103 scikit-learn bagging | 0.10113 | 0.08005 | |
117 | p/tlen | 2018-05-22 06:38 | 1.0.0 | decision tree, max_depth=10, f-measure on train=0.2918 scikit-learn decision-tree | 0.13576 | 0.13388 | |
110 | p/tlen | 2018-05-22 06:34 | 1.0.0 | decision tree, max_depth=20, f-measure on train=0.6321 scikit-learn decision-tree | 0.18003 | 0.19148 | |
123 | p/tlen | 2018-05-22 06:32 | 1.0.0 | forgotten test-A/out.tsv, f-measure on train=0.0609 scikit-learn decision-tree | 0.03313 | 0.03102 | |
103 | p/tlen | 2018-05-22 06:30 | 1.0.0 | decision tree, max_depth=5, f-measure on train=0.0609 scikit-learn decision-tree | 0.03313 | 0.21750 | |
102 | p/tlen | 2018-05-22 06:24 | 1.0.0 | decision tree, F-measure on train=0.9941 scikit-learn decision-tree | 0.22011 | 0.21750 | |
36 | [anonymized] | 2018-02-09 15:52 | 1.0.0 | 'baseline' neural-network | N/A | 0.42429 | |
55 | [anonymized] | 2018-02-09 12:42 | 1.0.0 | 'baseline' | N/A | 0.38481 | |
51 | [anonymized] | 2018-02-09 12:02 | 1.0.0 | 'baseline' | N/A | 0.39674 | |
58 | [anonymized] | 2018-02-09 11:12 | 1.0.0 | 'baseline' | N/A | 0.38057 | |
56 | [anonymized] | 2018-02-09 10:35 | 1.0.0 | 'baseline' | N/A | 0.38212 | |
54 | [anonymized] | 2018-02-09 09:53 | 1.0.0 | 'baseline' | N/A | 0.38857 | |
65 | [anonymized] | 2018-02-09 09:25 | 1.0.0 | 'baseline' | N/A | 0.36284 | |
60 | [anonymized] | 2018-02-09 09:12 | 1.0.0 | 'baseline' | N/A | 0.37440 | |
63 | [anonymized] | 2018-02-09 08:50 | 1.0.0 | 'baseline' | N/A | 0.36978 | |
67 | [anonymized] | 2018-02-09 08:23 | 1.0.0 | 'baseline' | N/A | 0.35445 | |
59 | [anonymized] | 2018-02-09 08:18 | 1.0.0 | baseline max_words=40 batch_size=512 nb_epoch=64 neural-network | N/A | 0.37637 | |
69 | [anonymized] | 2018-02-09 07:56 | 1.0.0 | baseline max_words=50 batch_size=512 nb_epoch=32 neural-network | N/A | 0.34892 | |
17 | [anonymized] | 2018-01-28 13:53 | 1.0.0 | test 11 | 0.45326 | 0.43913 | |
29 | [anonymized] | 2018-01-28 13:52 | 1.0.0 | test 11 | 0.45424 | 0.43052 | |
14 | [anonymized] | 2018-01-28 13:52 | 1.0.0 | test 11 | 0.45849 | 0.44207 | |
35 | [anonymized] | 2018-01-28 00:05 | 1.0.0 | test 11 | 0.45119 | 0.42569 | |
40 | [anonymized] | 2018-01-28 00:03 | 1.0.0 | test 11 | 0.44995 | 0.40997 | |
26 | [anonymized] | 2018-01-28 00:03 | 1.0.0 | test 11 | 0.45091 | 0.43424 | |
3 | [anonymized] | 2018-01-28 00:02 | 1.0.0 | test 11 | 0.45184 | 0.45519 | |
32 | [anonymized] | 2018-01-28 00:00 | 1.0.0 | test 11 | 0.45758 | 0.42813 | |
33 | [anonymized] | 2018-01-27 23:59 | 1.0.0 | test 11 | 0.45050 | 0.42735 | |
12 | [anonymized] | 2018-01-27 23:58 | 1.0.0 | test 11 | 0.45236 | 0.44244 | |
10 | [anonymized] | 2018-01-27 23:57 | 1.0.0 | test 11 | 0.45505 | 0.44394 | |
23 | [anonymized] | 2018-01-27 23:56 | 1.0.0 | test 11 | 0.45155 | 0.43682 | |
25 | [anonymized] | 2018-01-27 13:15 | 1.0.0 | test 11 | 0.45155 | 0.43463 | |
37 | [anonymized] | 2018-01-27 01:04 | 1.0.0 | test 11 | 0.44717 | 0.41822 | |
5 | [anonymized] | 2018-01-27 01:03 | 1.0.0 | test 11 | 0.45306 | 0.45387 | |
31 | [anonymized] | 2018-01-27 01:02 | 1.0.0 | test 11 | 0.45758 | 0.42813 | |
13 | [anonymized] | 2018-01-27 01:00 | 1.0.0 | test 11 | 0.45188 | 0.44223 | |
15 | [anonymized] | 2018-01-27 00:59 | 1.0.0 | test 11 | 0.45438 | 0.44090 | |
22 | [anonymized] | 2018-01-27 00:57 | 1.0.0 | test 11 | 0.45188 | 0.43763 | |
21 | [anonymized] | 2018-01-27 00:56 | 1.0.0 | test 11 | 0.45438 | 0.43763 | |
20 | [anonymized] | 2018-01-27 00:56 | 1.0.0 | test 11 | 0.45673 | 0.43763 | |
11 | [anonymized] | 2018-01-26 16:45 | 1.0.0 | test 10 | 0.46167 | 0.44289 | |
4 | [anonymized] | 2018-01-26 16:17 | 1.0.0 | test 10 | 0.45167 | 0.45438 | |
6 | [anonymized] | 2018-01-26 16:09 | 1.0.0 | test 10 | 0.46217 | 0.44931 | |
18 | [anonymized] | 2018-01-26 15:32 | 1.0.0 | test 10 | 0.44949 | 0.43825 | |
9 | [anonymized] | 2018-01-26 15:31 | 1.0.0 | test 10 | 0.45471 | 0.44504 | |
7 | [anonymized] | 2018-01-26 15:29 | 1.0.0 | test 10 | 0.45609 | 0.44689 | |
27 | [anonymized] | 2018-01-26 15:29 | 1.0.0 | test 10 | 0.45632 | 0.43122 | |
24 | [anonymized] | 2018-01-26 15:28 | 1.0.0 | test 9 | 0.45851 | 0.43470 | |
2 | [anonymized] | 2018-01-26 11:16 | 1.0.0 | test 8 | 0.46317 | 0.46489 | |
1 | [anonymized] | 2018-01-26 10:59 | 1.0.0 | Fixed class weight neural-network | 0.45671 | 0.46603 | |
30 | [anonymized] | 2018-01-26 10:40 | 1.0.0 | test 6 | 0.44521 | 0.42891 | |
19 | [anonymized] | 2018-01-26 10:36 | 1.0.0 | test 5 | 0.43805 | 0.43823 | |
28 | [anonymized] | 2018-01-26 10:32 | 1.0.0 | test 4 | 0.44978 | 0.43112 | |
8 | [anonymized] | 2018-01-24 23:53 | 1.0.0 | Found nice parameters neural-network | 0.45680 | 0.44607 | |
34 | [anonymized] | 2018-01-24 16:05 | 1.0.0 | test 2 | 0.45021 | 0.42614 | |
68 | [anonymized] | 2018-01-10 16:07 | 1.0.0 | test | 0.36588 | 0.35159 | |
41 | [anonymized] | 2018-01-10 15:14 | 1.0.0 | max_word=80, batch_size=256, activition=relu, optymizer=rmsprob, nb_epoch=200 GPU | 0.41722 | 0.40898 | |
38 | [anonymized] | 2018-01-09 19:32 | 1.0.0 | max_word=80, batch_size=256, activition=relu, optymizer=rmsprob, nb_epoch=200 neural-network | 0.41279 | 0.41575 | |
61 | [anonymized] | 2018-01-09 13:57 | 1.0.0 | Keras 2.1.2 | 0.38394 | 0.37312 | |
47 | [anonymized] | 2017-01-08 10:59 | 1.0.0 | approximate frequencies | 0.41749 | 0.40122 | |
39 | [anonymized] | 2017-01-07 22:08 | 1.0.0 | approximate frequencies | 0.41871 | 0.41393 | |
43 | [anonymized] | 2017-01-07 16:40 | 1.0.0 | spellcheck suggestions | 0.41217 | 0.40568 | |
44 | [anonymized] | 2017-01-06 18:24 | 1.0.0 | letter histograms | 0.41605 | 0.40561 | |
42 | [anonymized] | 2017-01-06 18:10 | 1.0.0 | improved learning rate | 0.41461 | 0.40665 | |
48 | [anonymized] | 2017-01-06 18:06 | 1.0.0 | improved spellchecking | 0.41153 | 0.40112 | |
52 | p/tlen | 2016-12-27 13:33 | 1.0.0 | ensemble of 3 simple neural networks | 0.41928 | 0.39376 | |
53 | p/tlen | 2016-12-27 11:31 | 1.0.0 | averaged 3 sub-NNs | 0.41583 | 0.39254 | |
57 | p/tlen | 2016-12-27 11:29 | 1.0.0 | averaged 3 sub-NNs | 0.41583 | 0.38095 | |
46 | p/tlen | 2016-12-27 09:56 | 1.0.0 | simple neural network with frequencies taken into account (tanh) | 0.42156 | 0.40284 | |
45 | p/tlen | 2016-12-27 09:14 | 1.0.0 | simple neural network with frequencies taken into account neural-network | 0.42670 | 0.40410 | |
72 | p/tlen | 2016-12-27 09:07 | 1.0.0 | simple neural network with frequencies taken into account | 0.42670 | 0.34614 | |
50 | p/tlen | 2016-12-26 17:18 | 1.0.0 | simple neural network without drop-out | 0.39933 | 0.40049 | |
66 | p/tlen | 2016-12-23 22:07 | 1.0.0 | simpler neural network but trained longer | 0.37556 | 0.35480 | |
77 | p/tlen | 2016-12-23 21:16 | 1.0.0 | even simpler neural network | 0.34912 | 0.33141 | |
122 | [anonymized] | 2016-12-19 20:14 | 1.0.0 | random yolo with correct output file xD | N/A | 0.06709 | |
124 | [anonymized] | 2016-12-19 20:08 | 1.0.0 | random yolo | N/A | N/A | |
49 | [anonymized] | 2016-12-15 20:26 | 1.0.0 | tuned parameters | 0.42095 | 0.40102 | |
71 | [anonymized] | 2016-12-13 23:47 | 1.0.0 | vw ngrams, suffixes, spellcheckers | 0.39271 | 0.34730 | |
80 | p/tlen | 2016-12-12 21:52 | 1.0.0 | stupid neural network by night | 0.33369 | 0.31117 | |
109 | p/tlen | 2016-12-10 14:50 | 1.0.0 | trivial solution (handcrafted one-liner) | 0.24359 | 0.19574 |