Guess a word in a gap in historic texts

Give a probability distribution for a word in a gap in a corpus of Polish historic texts spanning 1814-2013. This is a challenge for (temporal) language models. [ver. 1.0.0]

# submitter when ver. description dev-0 LogLossHashed dev-1 LogLossHashed test-A LogLossHashed
59 [anonymized] 2021-02-08 06:15 1.0.0 solution self-made lm 6.1745 6.1841 6.0733
151 [anonymized] 2021-02-04 20:29 1.0.0 ngram lm pytorch-nn 6.9101 N/A 6.9123
83 [anonymized] 2021-02-03 07:57 1.0.0 updated bigram self-made lm bigram 6.2850 6.3862 6.2673
95 [anonymized] 2021-01-27 10:23 1.0.0 TAU22 lm pytorch-nn 6.4696 6.4803 6.4151
94 [anonymized] 2021-01-25 00:41 1.0.0 TAU22 lm pytorch-nn 6.4696 6.4803 6.4151
96 [anonymized] 2021-01-25 00:31 1.0.0 TAU22 lm pytorch-nn 6.4696 6.4803 6.4201
167 [anonymized] 2021-01-16 16:29 1.0.0 lets try pytorch lm pytorch-nn 6.9606 6.9616 6.9731
88 [anonymized] 2021-01-13 02:38 1.0.0 v10 lm temporal pytorch-nn 6.3869 6.3945 6.3330
93 [anonymized] 2021-01-13 02:33 1.0.0 v9 6.4401 6.4464 6.3899
91 [anonymized] 2021-01-13 02:28 1.0.0 v8 6.3870 6.3946 6.3335
92 [anonymized] 2021-01-13 02:17 1.0.0 Merge remote-tracking branch 'origin/TAU-020' into TAU-020 6.4409 6.4468 6.3899
89 [anonymized] 2021-01-13 01:51 1.0.0 following_words;x_size=100;epochs=5;lr=0.001 lm pytorch-nn 6.3749 6.3775 6.3331
253 [anonymized] 2021-01-13 01:41 1.0.0 following_words;x_size=100;epochs=5;lr=0.001 lm pytorch-nn 6.3749 6.3775 N/A
109 [anonymized] 2021-01-13 00:00 1.0.0 v7 6.6176 6.6106 6.5937
108 [anonymized] 2021-01-12 23:55 1.0.0 v7 6.6056 6.6039 6.5885
104 [anonymized] 2021-01-12 23:43 1.0.0 v7 6.5773 6.5716 6.5581
169 [anonymized] 2021-01-12 22:40 1.0.0 TAU22 lm pytorch-nn 6.9961 6.9974 7.0113
119 [anonymized] 2021-01-12 22:26 1.0.0 v5 6.7626 6.7311 6.7022
149 [anonymized] 2021-01-12 17:48 1.0.0 run.py update lm pytorch-nn 6.9139 6.9013 6.9054
148 [anonymized] 2021-01-12 17:44 1.0.0 nn-gap-v1.0 6.9139 6.9013 6.9054
105 [anonymized] 2021-01-12 17:36 1.0.0 first solution 1 epoch 1000 texts best 15 lm pytorch-nn 6.6239 6.6617 6.5711
87 [anonymized] 2021-01-12 16:06 1.0.0 v4 6.3869 6.3945 6.3330
90 [anonymized] 2021-01-12 15:56 1.0.0 v3 6.3870 6.3946 6.3335
126 [anonymized] 2021-01-12 09:11 1.0.0 v3 6.7637 6.7738 6.7407
150 [anonymized] 2021-01-12 01:33 1.0.0 v3 6.9303 6.9267 6.9063
70 [anonymized] 2021-01-11 22:53 1.0.0 Solution lm pytorch-nn 6.1759 6.3140 6.1656
214 [anonymized] 2021-01-11 01:00 1.0.0 v2 7.3623 7.4396 7.3444
143 [anonymized] 2021-01-11 00:40 1.0.0 v1+years 6.8733 6.8783 6.8607
140 [anonymized] 2021-01-11 00:19 1.0.0 v1 6.8453 6.8709 6.8412
82 [anonymized] 2021-01-09 21:10 1.0.0 2 left, 2 right context lm pytorch-nn N/A 6.3009 6.2379
61 [anonymized] 2021-01-08 18:34 1.0.0 pytorch neural ngram model (3 previous words) lm pytorch-nn 6.1274 6.1896 6.0819
63 [anonymized] 2021-01-06 18:37 1.0.0 pytorch neural ngram model (3 previous words) lm pytorch-nn 6.1365 6.1994 6.0920
64 [anonymized] 2021-01-06 16:31 1.0.0 pytorch neural ngram model (3 previous words) lm pytorch-nn 6.1448 6.1987 6.0943
67 [anonymized] 2021-01-06 15:39 1.0.0 pytorch neural ngram model (3 previous words) lm pytorch-nn 6.1803 6.2305 6.1330
68 [anonymized] 2021-01-06 15:06 1.0.0 second try pytorch neural ngram model (3 previous words) lm pytorch-nn 6.1962 6.2449 6.1592
73 [anonymized] 2021-01-06 14:31 1.0.0 first try pytorch neural ngram model (3 previous words) lm pytorch-nn 6.2277 6.2578 6.1803
252 [anonymized] 2020-12-16 09:09 1.0.0 first try self-made lm N/A N/A N/A
127 [anonymized] 2020-12-16 08:52 1.0.0 poprawka tetragram self-made lm tetragram 6.7562 6.7703 6.7517
128 [anonymized] 2020-12-16 07:47 1.0.0 tetragram self-made lm tetragram 6.7562 6.7703 6.7611
74 [anonymized] 2020-12-16 07:16 1.0.0 python bigram self-made lm bigram 6.1865 6.3105 6.1837
223 [anonymized] 2020-12-15 22:14 1.0.0 RandLM first ready-made randlm 31.3001 33.2617 30.1634
216 [anonymized] 2020-12-13 14:17 1.0.0 solution self-made lm trigram N/A N/A 7.5152
251 [anonymized] 2020-12-13 14:05 1.0.0 change a N/A N/A N/A
250 [anonymized] 2020-12-13 13:41 1.0.0 add test N/A N/A N/A
224 [anonymized] 2020-12-09 21:19 1.0.0 bigram N/A N/A Infinity
249 [anonymized] 2020-12-09 09:51 1.0.0 model-size=10k self-made lm interpolation N/A N/A N/A
248 [anonymized] 2020-12-09 09:47 1.0.0 model-size=10k self-made lm interpolation N/A N/A N/A
247 [anonymized] 2020-12-09 09:45 1.0.0 model-size=10k self-made lm interpolation N/A N/A N/A
246 [anonymized] 2020-12-09 09:30 1.0.0 model-size=10k self-made lm interpolation N/A N/A N/A
97 [anonymized] 2020-12-08 16:27 1.0.0 solution self-made lm bigram 6.4696 6.4797 6.4201
153 [anonymized] 2020-12-08 15:50 1.0.0 finally self-made lm bigram 6.9443 7.0105 6.9236
213 [anonymized] 2020-12-08 13:38 1.0.0 please work better self-made lm bigram 7.2346 7.3019 7.2404
215 [anonymized] 2020-12-08 13:10 1.0.0 improved bigram (well, actually not, but the code is right now) self-made lm bigram 7.4204 7.4774 7.4397
168 [anonymized] 2020-12-08 11:06 1.0.0 bigrams solution self-made lm bigram 6.9956 7.0675 7.0056
165 [anonymized] 2020-12-08 09:18 1.0.0 trigrams-v1.8 self-made lm trigram 6.9468 6.9443 6.9510
172 [anonymized] 2020-12-08 08:52 1.0.0 trigrams-v1.7 7.0831 7.1273 7.0428
175 [anonymized] 2020-12-07 13:16 1.0.0 trigrams-v1.6 7.1635 7.2105 7.1446
170 [anonymized] 2020-12-07 13:09 1.0.0 trigrams-v1.5 7.0347 7.0889 7.0170
220 [anonymized] 2020-12-07 12:33 1.0.0 trigrams-v1.4 9.5093 9.3352 9.4255
218 [anonymized] 2020-12-07 12:25 1.0.0 trigrams-v1.3 8.5079 8.4386 8.4943
219 [anonymized] 2020-12-07 12:17 1.0.0 trigrams-v1.2 9.1281 8.9452 9.1356
221 [anonymized] 2020-12-07 11:44 1.0.0 trigrams 9.6720 9.4952 9.5646
69 [anonymized] 2020-12-04 00:27 1.0.0 solution self-made lm bigram 6.1705 6.3034 6.1610
101 [anonymized] 2020-12-03 03:55 1.0.0 v23.3 ready-made kenlm lm 6.2619 6.4126 6.4908
102 [anonymized] 2020-12-03 03:53 1.0.0 v23-6 6.2715 6.4253 6.5054
100 [anonymized] 2020-12-03 03:51 1.0.0 v23-5 6.2619 6.4126 6.4908
110 [anonymized] 2020-12-02 22:19 1.0.0 v23-4 6.3706 6.5414 6.6331
111 [anonymized] 2020-12-02 22:04 1.0.0 v23-3 6.3755 6.5455 6.6354
113 [anonymized] 2020-12-02 16:23 1.0.0 Merge remote-tracking branch 'origin/TAU-011' into TAU-011 6.3739 6.5459 6.6385
117 [anonymized] 2020-12-02 15:52 1.0.0 v27 6.5396 6.6421 6.6733
123 [anonymized] 2020-12-02 13:04 1.0.0 Trigram slef-made self-made lm trigram 6.7004 6.7900 6.7172
122 [anonymized] 2020-12-02 09:28 1.0.0 Trigram self-made self-made lm trigram 6.7004 6.7900 6.7172
118 [anonymized] 2020-12-02 08:14 1.0.0 v26 6.5515 6.6369 6.6791
129 [anonymized] 2020-12-02 08:10 1.0.0 v25 6.7038 6.7513 6.7635
146 [anonymized] 2020-12-02 07:51 1.0.0 v24 6.8643 6.8778 6.8834
145 [anonymized] 2020-12-02 07:51 1.0.0 Merge remote-tracking branch 'origin/TAU-011' into TAU-011 6.8643 6.8778 6.8834
112 [anonymized] 2020-12-02 02:12 1.0.0 v23 ready-made kenlm lm 6.3738 6.5459 6.6385
115 [anonymized] 2020-12-02 01:57 1.0.0 v22 6.3786 6.5490 6.6404
114 [anonymized] 2020-12-02 01:47 1.0.0 v21 6.3733 6.5457 6.6396
120 [anonymized] 2020-12-02 01:04 1.0.0 v20 6.4265 6.6039 6.7040
116 [anonymized] 2020-12-02 00:59 1.0.0 v19 6.4001 6.5745 6.6726
103 [anonymized] 2020-12-01 22:55 1.0.0 trigram lm self-made lm trigram 6.6292 6.6930 6.5452
130 [anonymized] 2020-12-01 18:52 1.0.0 v18 6.5392 6.6772 6.7758
132 [anonymized] 2020-12-01 18:51 1.0.0 v17 6.5426 6.6808 6.7786
217 [anonymized] 2020-12-01 18:08 1.0.0 v16 7.3384 7.4831 7.6228
131 [anonymized] 2020-12-01 18:03 1.0.0 v15 6.5407 6.6787 6.7770
135 [anonymized] 2020-12-01 17:48 1.0.0 v14 6.5694 6.7099 6.8102
142 [anonymized] 2020-12-01 17:40 1.0.0 v13 6.6046 6.7479 6.8504
166 [anonymized] 2020-12-01 17:35 1.0.0 v12 6.7042 6.8543 6.9623
171 [anonymized] 2020-12-01 17:20 1.0.0 v11 6.7770 6.9314 7.0428
176 [anonymized] 2020-12-01 17:15 1.0.0 v10 6.8756 7.0352 7.1509
174 [anonymized] 2020-11-30 20:45 1.0.0 v9 7.2720 7.2878 7.1423
141 [anonymized] 2020-11-30 19:36 1.0.0 v8 6.9470 6.9615 6.8461
222 [anonymized] 2020-11-28 13:15 1.0.0 v3 9.6603 9.7094 9.9624
154 [anonymized] 2020-11-27 23:27 1.0.0 v1 7.0538 6.9977 6.9289
1 kubapok 2020-10-13 08:42 1.0.0 regular roberta epoch 190 4.2993 4.5402 4.3285
204 kubapok 2020-10-11 20:32 1.0.0 roberta first token embedding epoch 190 4.3091 4.5435 4.3397
207 kubapok 2020-10-11 20:17 1.0.0 roberta first token embedding epoch 182 4.3449 4.5755 4.3700
208 kubapok 2020-10-10 08:39 1.0.0 regular roberta epoch 182 4.3448 4.5758 4.3747
203 kubapok 2020-10-09 10:56 1.0.0 roberta z embeddingiem pierwszy token 4.4648 4.4763 4.2801
202 kubapok 2020-10-08 20:21 1.0.0 regularna roberta 4.4606 4.4763 4.2801
201 kubapok 2020-06-29 21:54 1.0.0 polish roberta year aware, but not so clever, further training 4.2580 4.4763 4.2801
205 kubapok 2020-06-22 20:02 1.0.0 polish roberta finetunned year aware, but not so clever 4.3035 4.5484 4.3466
210 kubapok 2020-06-13 21:35 1.0.0 polish roberta base no finetunning 4.8964 5.1527 4.9802
209 kubapok 2020-06-13 20:43 1.0.0 polish roberta large no finetunning 4.7162 4.9455 4.8072
206 kubapok 2020-06-02 17:38 1.0.0 polish roberta finetunned low lr transformer fairseq 4.3361 4.5718 4.3698
211 kubapok 2020-02-29 16:05 1.0.0 bigger transformer, longer training 5.0819 N/A 5.0309
212 kubapok 2020-02-25 20:33 1.0.0 transformer year unaware 5.2537 N/A 5.1726
155 [anonymized] 2020-01-16 18:12 1.0.0 IRLSTM 3-gram lm N/A N/A 6.9314
156 [anonymized] 2020-01-15 19:39 1.0.0 IRSTLM N/A N/A 6.9314
157 [anonymized] 2020-01-15 19:37 1.0.0 IRSTLM N/A N/A 6.9314
200 [anonymized] 2020-01-15 19:35 1.0.0 IRLSTM N/A N/A NaN
199 [anonymized] 2020-01-15 19:31 1.0.0 IRLSTM N/A N/A NaN
164 [anonymized] 2020-01-15 19:20 1.0.0 IRSTLM N/A N/A 6.9315
163 [anonymized] 2020-01-15 19:09 1.0.0 IRSTLM N/A N/A 6.9315
160 [anonymized] 2020-01-15 19:04 1.0.0 IRSTLM N/A N/A 6.9314
159 [anonymized] 2020-01-15 19:02 1.0.0 IRSTLM N/A N/A 6.9314
158 [anonymized] 2020-01-15 18:59 1.0.0 IRSTLM N/A N/A 6.9314
245 [anonymized] 2020-01-15 10:25 1.0.0 IRSTLM N/A N/A N/A
180 [anonymized] 2020-01-15 10:25 1.0.0 IRSTLM epsilon=0 N/A N/A 7.2184
244 [anonymized] 2020-01-15 10:20 1.0.0 IRSTLM N/A N/A N/A
179 [anonymized] 2020-01-15 10:20 1.0.0 IRSTLM epsilon=0 N/A N/A 7.2184
243 [anonymized] 2020-01-15 09:56 1.0.0 IRSTLM N/A N/A N/A
178 [anonymized] 2020-01-15 09:56 1.0.0 IRSTLM epsilon=0.01 N/A N/A 7.2184
242 [anonymized] 2020-01-15 09:53 1.0.0 IRSTLM N/A N/A N/A
177 [anonymized] 2020-01-15 09:53 1.0.0 IRSTLM epsilon=0.01 N/A N/A 7.2184
241 [anonymized] 2020-01-15 09:49 1.0.0 IRSTLM epsilon=0.01 N/A N/A N/A
240 [anonymized] 2020-01-15 09:49 1.0.0 IRSTLM N/A N/A N/A
188 [anonymized] 2020-01-13 14:54 1.0.0 IRSTLM last result lm N/A N/A 8.4198
192 [anonymized] 2020-01-09 23:04 1.0.0 IRSTLM third solution N/A N/A 12.7659
194 [anonymized] 2020-01-09 22:20 1.0.0 IRSTLM third solution N/A N/A 13.9740
193 [anonymized] 2020-01-09 22:12 1.0.0 IRSTLM third solution N/A N/A 13.2266
190 [anonymized] 2020-01-09 21:15 1.0.0 IRSTLM second solution N/A N/A 10.7553
191 [anonymized] 2020-01-09 19:21 1.0.0 IRSTLM second solution N/A N/A 12.5241
239 [anonymized] 2020-01-08 09:21 1.0.0 IRLSTM first solution lm N/A N/A N/A
238 [anonymized] 2019-12-10 20:35 1.0.0 solution lm N/A N/A N/A
133 [anonymized] 2019-11-30 22:48 1.0.0 3gram outfile format fix lm trigram N/A N/A 6.8032
72 [anonymized] 2019-11-27 10:19 1.0.0 Simple bigram model lm 6.1832 6.3083 6.1802
237 [anonymized] 2019-11-27 10:04 1.0.0 Simple trigram lm N/A N/A N/A
49 kubapok 2019-11-25 10:42 1.0.0 year aware 4 splits statistical 5.8219 N/A 5.7973
40 kubapok 2019-11-25 10:36 1.0.0 year aware 2 splits 5.7372 N/A 5.6667
124 [anonymized] 2019-11-20 17:07 1.0.0 better bigram solution, nananana lm 6.7205 6.7565 6.7249
183 [anonymized] 2019-11-18 16:30 1.0.0 bigram solution, sialala lm 7.3424 7.2223 7.2732
38 kubapok 2019-11-17 08:31 1.0.0 self made LM 3grams with fallback to 2grams and 1grams 5.6790 N/A 5.6063
198 [anonymized] 2019-11-13 16:32 1.0.0 Simple bigram model lm Infinity Infinity Infinity
125 [anonymized] 2019-11-13 12:29 1.0.0 My bigram guess a word solution lm 6.7279 6.7631 6.7309
236 [anonymized] 2019-11-13 09:33 1.0.0 Simple bigram model lm N/A N/A N/A
66 kubapok 2019-11-12 06:52 1.0.0 bigram model, equal distribution N/A N/A 6.1264
78 kubapok 2019-11-11 18:14 1.0.0 stupid solution N/A N/A 6.2078
162 kubapok 2019-11-11 11:45 1.0.0 very baseline N/A N/A 6.9315
21 p/tlen 2019-05-24 09:39 1.0.0 LM model used (applica-lm-retro-gap-transformer-bpe-bigger-preproc=minimalistic-left_to_right-lang=pl-5.3.0.0.bin) attention-dropout=0.1 attention-heads=8 bptt=50 chunksize=10000 clip=0.25 dropout=0.1 early-stopping=15 early-stopping-type=iteration [...] lm word-level transformer 5.2179 5.4184 5.1606
184 p/tlen 2019-05-19 02:53 1.0.0 LM model trained on 20190519 (applica-lm-retro-gap-transformer-bigger-preproc=minimalistic-left_to_right-lang=pl-5.3.0.0.bin) best-epoch=90 bptt=50 chunksize=10000 clip=0.25 early-stopping=15 early-stopping-type=iteration epochs=100 epochs-done=90 [...] lm word-level 7.3604 7.3470 7.3037
48 p/tlen 2019-05-17 19:14 1.0.0 LM model used (model.bin) attention-dropout=0.1 attention-heads=8 bptt=50 chunksize=10000 clip=0.25 dropout=0.1 early-stopping=20 early-stopping-type=iteration [...] lm word-level transformer 5.8551 5.9289 5.7924
20 p/tlen 2019-05-16 10:31 1.0.0 LM model trained on 20190516 (applica-lm-retro-gap-transformer-bpe-bigger-preproc=minimalistic-left_to_right-lang=pl-5.3.0.0.bin) attention-dropout=0.1 attention-heads=8 beam-search-depth=2 best-epoch=80 bptt=50 chunksize=10000 clip=0.25 dropout=0.1 [...] lm word-level transformer left-to-right bpe 5.2138 5.4159 5.1584
23 p/tlen 2019-05-14 04:53 1.0.0 LM model trained on 20190514 (applica-lm-retro-gap-transformer-bpe-preproc=minimalistic-left_to_right-lang=pl-5.2.0.0.bin) attention-dropout=0.1 attention-heads=8 beam-search-depth=2 best-epoch=75 bptt=50 chunksize=10000 clip=0.25 dropout=0.1 [...] lm word-level transformer left-to-right bpe 5.2746 5.4622 5.2050
25 p/tlen 2019-05-11 00:49 1.0.0 LM model used (model.bin) attention-dropout=0.1 attention-heads=8 beam-search-depth=2 bptt=50 chunksize=10000 clip=0.25 dropout=0.1 early-stopping=20 [...] lm word-level transformer left-to-right bpe 5.3047 5.4820 5.2355
32 p/tlen 2019-05-10 13:58 1.0.0 LM model used (model.bin) attention-dropout=0.1 attention-heads=8 beam-search-depth=2 bptt=50 chunksize=10000 clip=0.25 dropout=0.1 early-stopping=20 [...] lm word-level transformer left-to-right bpe 5.3522 5.5277 5.2825
28 p/tlen 2019-05-10 01:27 1.0.0 LM model used (model.bin) attention-dropout=0.1 attention-heads=8 bptt=50 chunksize=10000 clip=0.25 dropout=0.1 early-stopping=20 early-stopping-type=iteration [...] lm word-level transformer 5.3083 5.4859 5.2453
27 p/tlen 2019-05-08 20:38 1.0.0 LM model used (model.bin) attention-dropout=0.1 attention-heads=8 bptt=50 chunksize=10000 clip=0.25 dropout=0.1 early-stopping=20 early-stopping-type=iteration [...] lm word-level transformer 5.3070 5.4849 5.2377
30 p/tlen 2019-05-08 11:24 1.0.0 LM model used (model.bin) attention-dropout=0.1 attention-heads=8 beam-search-depth=0 bptt=50 chunksize=10000 clip=0.25 dropout=0.1 early-stopping=20 [...] lm word-level transformer left-to-right bpe 5.3200 5.4907 5.2505
26 p/tlen 2019-05-08 08:59 1.0.0 LM model used (model.bin) attention-dropout=0.1 attention-heads=8 beam-search-depth=1 bptt=50 chunksize=10000 clip=0.25 dropout=0.1 early-stopping=20 [...] word-level transformer left-to-right bpe 5.3071 5.4841 5.2370
106 p/tlen 2019-04-17 11:25 1.0.0 LM model used (model.bin) attention-dropout=0.1 attention-heads=8 bptt=50 chunksize=10000 clip=0.25 dropout=0.1 early-stopping=20 early-stopping-type=iteration [...] lm word-level transformer 6.5591 6.6602 6.5816
24 p/tlen 2019-04-12 04:40 1.0.0 LM model used (bi-transformer.bin) aggregator=MIN lm word-level transformer 5.3190 5.5181 5.2311
5 p/tlen 2019-04-12 04:40 1.0.0 LM model used (bi-transformer.bin) aggregator=MAX lm word-level transformer 4.9537 5.1992 4.9031
4 p/tlen 2019-04-12 04:40 1.0.0 LM model used (bi-transformer.bin) aggregator=RMS lm word-level transformer 4.9381 5.1868 4.8886
3 p/tlen 2019-04-12 04:40 1.0.0 LM model used (bi-transformer.bin) aggregator=MEAN lm word-level transformer 4.9128 5.1678 4.8653
2 p/tlen 2019-04-12 04:40 1.0.0 LM model used (bi-transformer.bin) aggregator=GEO lm word-level transformer 4.9048 5.1608 4.8570
139 p/tlen 2019-04-10 22:39 1.0.0 LM model used (transformer-sumo.bin) lm word-level transformer 6.8188 6.8351 6.8170
9 p/tlen 2019-04-10 12:41 1.0.0 LM model used (bi-partially-casemarker-transformer.bin) lm word-level transformer 5.0075 5.2557 4.9933
8 p/tlen 2019-04-10 09:54 1.0.0 LM model used (bi-transformer.bin) lm word-level transformer 4.9959 5.2376 4.9875
22 p/tlen 2019-04-10 00:09 1.0.0 LM model used (model.bin) lm word-level transformer right-to-left 5.2604 5.4692 5.2021
136 p/tlen 2019-04-06 11:23 1.0.0 LM model used (model.bin) lm word-level transformer 6.8933 6.7577 6.8104
138 p/tlen 2019-04-06 00:39 1.0.0 LM model used (model.bin) lm word-level transformer 6.8781 6.7650 6.8168
137 p/tlen 2019-04-05 15:29 1.0.0 LM model trained on 20190405 (applica-lm-retro-gap-transformer-frage-rvt-preproc=minimalistic-left_to_right-lang=pl-5.2.0.0.bin) attention-dropout=0.1 attention-heads=8 best-epoch=65 bptt=50 chunksize=10000 clip=0.25 dropout=0.1 early-stopping=20 [...] lm word-level transformer 6.8781 6.7650 6.8168
29 p/tlen 2019-04-01 13:14 1.0.0 LM model used (model.bin) lm word-level transformer left-to-right 5.3162 5.5091 5.2502
14 p/tlen 2019-04-01 10:16 1.0.0 LM model trained on 20190331 (applica-lm-retro-gap-bilstm-case-marker-preproc=minimalistic-bidirectional-lang=pl-5.2.0.0.bin) lm word-level bilstm casemarker 5.0902 5.3020 5.0304
35 p/tlen 2019-03-31 23:09 1.0.0 LM model trained on 20190331 (applica-lm-retro-gap-bilstm-case-marker-preproc=minimalistic-bidirectional-lang=pl-5.2.0.0.bin) best-epoch=97 bptt=35 chunksize=10000 clip=0.25 dropout=0.5 early-stopping=20 early-stopping-type=iteration enc-dropout=0.5 [...] lm word-level bilstm casemarker 5.4263 5.6073 5.3378
84 p/tlen 2019-03-30 12:13 1.0.0 LM model used (model.bin) lm word-level transformer 6.4247 6.4674 6.2930
99 p/tlen 2019-03-30 05:29 1.0.0 LM model trained on 20190330 (applica-lm-retro-gap-transformer-frage-casemarker-preproc=minimalistic-left_to_right-lang=pl-5.2.0.0.bin) attention-dropout=0.1 attention-heads=8 best-epoch=20 bptt=50 chunksize=10000 clip=0.25 dropout=0.1 early-stopping=20 [...] lm word-level transformer 6.6148 6.6728 6.4872
12 p/tlen 2019-03-29 02:33 1.0.0 LM model trained on 20190329 (applica-lm-retro-gap-bilstm-frage-fixed-vocab-preproc=minimalistic-bidirectional-lang=pl-5.2.0.0.bin) best-epoch=103 bptt=35 chunksize=10000 clip=0.25 dropout=0.5 early-stopping=20 early-stopping-type=iteration enc-dropout=0.5 [...] lm word-level bilstm 5.0710 5.2996 5.0022
6 p/tlen 2019-03-21 14:11 1.0.0 per-period models combined (100/50) bptt=35 chunksize=10000 clip=0.25 dropout=0.5 early-stopping=8 early-stopping-type=epoch enc-dropout=0.5 enc-highways=0 [...] lm word-level bilstm 5.0234 5.2742 4.9768
7 p/tlen 2019-03-21 09:04 1.0.0 per-period models combined (100/50) bptt=35 chunksize=10000 clip=0.25 dropout=0.5 early-stopping=8 early-stopping-type=epoch enc-dropout=0.5 enc-highways=0 [...] lm word-level bilstm 5.0241 5.2751 4.9769
10 p/tlen 2019-03-21 08:31 1.0.0 two BiLSTMs, one for each 100 years bptt=35 chunksize=10000 clip=0.25 dropout=0.5 early-stopping=8 early-stopping-type=epoch enc-dropout=0.5 enc-highways=0 [...] lm word-level bilstm 5.0337 5.2924 4.9956
17 p/tlen 2019-03-20 04:14 1.0.0 LM model trained on 20190320 (applica-lm-retro-gap-train-1864-1963-bilstm-frage-1814-1913-preproc=minimalistic-bidirectional-lang=pl-5.2.0.0.bin) best-epoch=35 bptt=35 chunksize=10000 clip=0.25 dropout=0.5 early-stopping=8 early-stopping-type=epoch enc-dropout=0.5 [...] lm word-level bilstm 5.1606 5.3497 5.0825
13 p/tlen 2019-03-19 21:11 1.0.0 LM model trained on 20190319 (applica-lm-retro-gap-train-1914-2013-bilstm-frage-1914-2013-preproc=minimalistic-bidirectional-lang=pl-5.2.0.0.bin) best-epoch=63 bptt=35 chunksize=10000 clip=0.25 dropout=0.5 early-stopping=20 early-stopping-type=iteration enc-dropout=0.5 [...] lm word-level bilstm 5.1546 5.3037 5.0229
31 p/tlen 2019-03-16 19:24 1.0.0 LM model trained on 20190316 (applica-lm-retro-gap-train-1814-1913-bilstm-frage-1814-1913-preproc=minimalistic-bidirectional-lang=pl-5.2.0.0.bin) best-epoch=32 bptt=35 chunksize=10000 clip=0.25 dropout=0.5 early-stopping=8 early-stopping-type=epoch enc-dropout=0.5 [...] lm word-level bilstm 5.2199 5.4381 5.2651
189 p/tlen 2019-03-10 17:09 1.0.0 LM model trained on 20190310 (applica-lm-retro-gap-transformer-frage-preproc=minimalistic-left_to_right-lang=pl-5.2.0.0.bin) attention-dropout=0.1 attention-heads=8 best-epoch=74 bptt=50 chunksize=10000 clip=0.25 dropout=0.1 early-stopping=20 [...] lm word-level transformer 9.5350 9.4320 9.2231
19 p/tlen 2019-02-22 22:52 1.0.0 LM model used (model.bin) lm word-level bilstm 5.1855 5.3806 5.1346
11 p/tlen 2019-02-18 15:14 1.0.0 LM model trained on 20190218 (applica-lm-retro-gap-retro-gap-frage-preproc=minimalistic-bidirectional-lang=pl-5.2.0.0.bin) best-epoch=95 bptt=35 chunksize=10000 clip=0.25 dropout=0.5 early-stopping=20 early-stopping-type=iteration enc-dropout=0.5 [...] lm word-level bilstm frage 5.0696 5.2951 5.0006
37 p/tlen 2019-02-08 23:03 1.0.0 LM model trained on 20190208 (applica-lm-train-tokenized-lowercased-shuffled-bilstm-all-preproc=minimalistic-bidirectional-lang=pl-5.2.0.0.bin) best-epoch=1 bptt=35 chunksize=10000 clip=0.25 dropout=0.5 early-stopping=40 enc-dropout=0.5 enc-highways=0 [...] lm word-level bilstm 5.4361 5.5855 5.3822
36 p/tlen 2019-02-07 07:58 1.0.0 LM model trained on 20190207 (applica-lm-train-tokenized-lowercased-shuffled-bilstm-all-preproc=minimalistic-bidirectional-lang=pl-5.2.0.0.bin) best-epoch=1 bptt=35 chunksize=10000 clip=0.25 dropout=0.5 early-stopping=10 enc-dropout=0.5 enc-highways=0 [...] lm word-level bilstm 5.4315 5.5867 5.3780
15 p/tlen 2019-02-02 09:49 1.0.0 LM model trained on 20190202 (applica-lm-retro-gap-bilstm-word-preproc=minimalistic-bidirectional-lang=pl-5.1.9.0.bin) best-epoch=79 bptt=35 chunksize=10000 clip=0.25 dropout=0.5 enc-dropout=0.5 enc-highways=0 epochs=80 [...] lm word-level bilstm 5.1253 5.3486 5.0603
39 p/tlen 2019-01-30 19:56 1.0.0 LM model trained on 20190130 (applica-lm-retro-gap-transformer-word-preproc=minimalistic-left_to_right-lang=pl-5.1.9.0.bin) attention-heads=8 best-epoch=80 bptt=35 chunksize=10000 clip=0.25 dropout=0.5 enc-dropout=0.5 enc-highways=0 [...] lm word-level transformer 5.7237 5.8370 5.6476
42 p/tlen 2019-01-28 05:16 1.0.0 LM model trained on 20190128 (applica-lm-retro-gap-transformer-word-preproc=minimalistic-left_to_right-lang=pl-5.1.9.0.bin) attention-heads=8 best-epoch=48 bptt=35 chunksize=10000 clip=0.25 dropout=0.5 enc-dropout=0.5 enc-highways=0 [...] lm word-level transformer 5.7902 5.8972 5.7039
34 p/tlen 2019-01-09 16:30 1.0.0 LM model trained on 20190109 (applica-lm-retro-gap-bilstm-cnn-preproc=minimalistic-bidirectional-lang=pl-5.1.8.0.bin) best-epoch=50 bptt=35 char-emb-size=16 chunksize=10000 clip=0.25 dropout=0.3 enc-dropout=0.3 enc-highways=2 [...] lm char-n-grams bilstm 5.4438 5.5773 5.3202
16 p/tlen 2018-12-30 05:32 1.0.0 LM model trained on 20181230 (applica-lm-retro-gap-bilstm-preproc=minimalistic-bidirectional-lang=pl-5.1.8.0.bin) best-epoch=49 bptt=35 chunksize=10000 clip=0.25 dropout=0.5 enc-dropout=0.5 enc-highways=0 epochs=50 [...] lm word-level bilstm 5.1365 5.3476 5.0632
33 p/tlen 2018-12-27 21:24 1.0.0 LM model trained on 20181227 (applica-lm-retro-gap-bilstm-preproc=minimalistic-bidirectional-lang=pl-5.1.8.0.bin) best-epoch=1 bptt=35 chunksize=10000 clip=0.25 dropout=0.5 enc-dropout=0.5 enc-highways=0 epochs=1 [...] lm word-level bilstm 5.4143 5.5581 5.3177
18 p/tlen 2018-12-27 10:00 1.0.0 LM model trained20181225 (applica-lm-retro-gap-bilstm-preproc=minimalistic-bidirectional-lang=en-5.1.8.0.bin) best-epoch=39 bptt=35 chunksize=10000 clip=0.25 dropout=0.5 enc-dropout=0.5 enc-highways=0 epochs=40 [...] lm 5.2085 N/A 5.1303
45 p/tlen 2018-09-02 20:20 1.0.0 simple 2-layer LSTM, left-to-right epochs=1 neural-network lm lstm left-to-right 5.8425 5.8765 5.7359
196 [anonymized] 2018-01-28 07:51 1.0.0 trigrams_fixed self-made lm trigram N/A N/A 19.1101
46 [anonymized] 2018-01-24 14:39 1.0.0 simple neural network, context 2 words ahead 2 words behind neural-network 5.8672 6.0007 5.7395
47 kaczla 2018-01-17 11:20 1.0.0 simple neural network - nb_of_epochs=3, batch_size=2048 neural-network 5.8751 5.9999 5.7839
51 kaczla 2018-01-16 18:52 1.0.0 simple neural network - nb_of_epochs=2 neural-network 5.9285 6.0385 5.8193
52 kaczla 2018-01-16 18:13 1.0.0 simple neural network - nb_of_epochs=4 neural-network 5.9463 6.0446 5.8514
57 kaczla 2018-01-16 17:17 1.0.0 simple neural network - decrease batch_size neural-network 6.1810 6.2569 6.0581
65 [anonymized] 2018-01-15 18:11 1.0.0 Bigrams model, 100 best words stupid self-made lm bigram N/A 6.3638 6.1097
235 [anonymized] 2018-01-09 18:26 1.0.0 ??? stupid self-made lm bigram N/A N/A N/A
234 [anonymized] 2018-01-09 18:08 1.0.0 Bigrams model, 100 best words stupid self-made lm bigram N/A N/A N/A
53 p/tlen 2018-01-03 06:07 1.0.0 a very simple (non-recurrent) neural network, looking one word behind and one word ahead (train on all data), dictionary size=40000 neural-network 5.9766 6.0881 5.8648
195 [anonymized] 2018-01-02 18:14 1.0.0 'trigrams' self-made lm trigram N/A N/A 14.5507
233 [anonymized] 2018-01-02 17:26 1.0.0 'trigrams' N/A N/A N/A
54 p/tlen 2018-01-02 16:23 1.0.0 a very simple (non-recurrent) neural network, looking one word behind and one word ahead neural-network 5.9794 6.0982 5.8990
60 [anonymized] 2017-12-13 14:54 1.0.0 unigram with temporal info, best 100, two periods (1813, 1913) (1913, 2014) self-made lm temporal unigram 6.1654 6.1828 6.0816
62 [anonymized] 2017-12-13 14:44 1.0.0 unigram with temporal info, best 100, 2 periods (1813, 1913) (1913, 2014) self-made lm temporal unigram 6.1717 6.2016 6.0893
71 [anonymized] 2017-12-13 14:41 1.0.0 unigram with temporal model, 25 best self-made 6.2397 6.2592 6.1729
75 kaczla 2017-12-12 20:45 1.0.0 3-gram with prune, best 1, best oov ready-made kenlm lm 6.1260 6.2991 6.1896
56 kaczla 2017-12-12 20:42 1.0.0 3-gram with prune, best 2, best oov ready-made kenlm lm 5.9662 6.1685 6.0105
55 kaczla 2017-12-12 20:41 1.0.0 3-gram with prune, best 3, best oov ready-made kenlm lm 5.8803 6.0738 5.9181
50 kaczla 2017-12-12 20:38 1.0.0 3-gram with prune, best 5, best oov ready-made kenlm lm 5.8022 5.9837 5.8182
44 kaczla 2017-12-12 20:37 1.0.0 3-gram with prune, best 10, best oov ready-made kenlm lm 5.7428 5.9032 5.7196
41 kaczla 2017-12-12 20:35 1.0.0 3-gram with prune, best 15, best oov ready-made kenlm lm 5.7367 5.8767 5.7006
43 kaczla 2017-12-12 20:32 1.0.0 3-gram with prune, best 25, best oov ready-made kenlm lm 5.7500 5.8788 5.7052
80 kaczla 2017-12-12 19:19 1.0.0 3-gram with prune, best 1 ready-made kenlm lm 6.1473 6.3361 6.2166
81 kaczla 2017-12-12 19:17 1.0.0 3-gram with prune, best 2 ready-made kenlm lm 6.1808 6.4349 6.2362
85 kaczla 2017-12-12 19:14 1.0.0 3-gram with prune, best 3 ready-made kenlm lm 6.2590 6.5174 6.3085
98 kaczla 2017-12-05 21:39 1.0.0 3-gram with prune, best 5 ready-made kenlm lm 6.4040 6.6586 6.4228
107 kaczla 2017-12-05 21:38 1.0.0 3-gram with prune, best 10 ready-made kenlm lm 6.6364 6.8789 6.5879
121 kaczla 2017-12-05 21:35 1.0.0 3-gram with prune, best 15 ready-made kenlm lm 6.7882 7.0033 6.7119
144 kaczla 2017-12-05 21:33 1.0.0 3-gram with prune, best 25 ready-made kenlm lm 6.9749 7.1766 6.8763
173 kaczla 2017-12-05 21:30 1.0.0 3-gram with prune, best 50 ready-made kenlm lm 7.2401 7.4038 7.1059
185 kaczla 2017-12-05 21:24 1.0.0 3-gram with prune, best 100 ready-made kenlm lm 7.4523 7.6464 7.3087
79 [anonymized] 2017-06-29 22:47 1.0.0 Order 4 N/A N/A 6.2111
86 [anonymized] 2017-06-29 18:38 1.0.0 order 2 N/A N/A 6.3262
77 [anonymized] 2017-06-29 15:12 1.0.0 Update source code; kenlm order=3 tokenizer.perl from moses. best 100 results, text mode. ready-made kenlm lm N/A N/A 6.1898
76 [anonymized] 2017-06-29 15:08 1.0.0 added wildcard N/A N/A 6.1898
197 [anonymized] 2017-06-29 12:29 1.0.0 first 100 N/A N/A Infinity
232 [anonymized] 2017-06-28 13:23 1.0.0 top 100 N/A N/A N/A
147 [anonymized] 2017-06-28 08:47 1.0.0 test 2 ready-made neural-network N/A N/A 6.8956
186 [anonymized] 2017-06-27 19:14 1.0.0 first test ready-made neural-network N/A N/A 7.5236
231 [anonymized] 2017-06-15 23:29 1.0.0 First try N/A N/A N/A
134 [anonymized] 2017-05-16 04:31 1.0.0 zad 16 self-made lm N/A N/A 6.8056
58 [anonymized] 2017-04-24 16:42 1.0.0 unigramy, n=100, v3 self-made lm 6.1745 6.1841 6.0733
187 [anonymized] 2017-04-24 16:32 1.0.0 unigramy, n=100, v2 self-made lm 8.0610 8.0714 7.8460
230 [anonymized] 2017-04-24 16:29 1.0.0 unigramy, n=100 N/A N/A N/A
229 [anonymized] 2017-04-24 16:24 1.0.0 unigramy, n=1000 7.6808 7.7246 N/A
182 [anonymized] 2017-04-24 15:14 1.0.0 unigramy (dobre kodowanie) v2 self-made lm 7.3661 7.3596 7.2467
228 [anonymized] 2017-04-24 15:11 1.0.0 unigramy (dobre kodowanie) N/A N/A N/A
181 [anonymized] 2017-04-23 17:57 1.0.0 Unigram (problem kodowania) 7.3661 7.3596 7.2467
227 [anonymized] 2017-04-23 17:53 1.0.0 Unigram (problem kodowania) 7.3661 N/A N/A
225 [anonymized] 2017-04-23 17:46 1.0.0 Unigram (problem kodowania) N/A N/A N/A
226 [anonymized] 2017-04-23 17:43 1.0.0 Unigram (problem kodowania) N/A N/A N/A
152 p/tlen 2017-04-10 06:22 1.0.0 uniform probability except for comma stupid 6.9116 6.9585 6.9169
161 p/tlen 2017-04-10 06:18 1.0.0 uniform probability stupid 6.9315 6.9315 6.9315

Submission graph

Graphs by parameters

beam-search-depth

[direct link]

best-epoch

[direct link]

dropout

[direct link]

early-stopping

[direct link]

enc-dropout

[direct link]

enc-highways

[direct link]

epochs

[direct link]

epochs-done

[direct link]

execution-time

[direct link]

ffn-emb-size

[direct link]

hidden-size

[direct link]

layers

[direct link]

trainable-params

[direct link]

validation-perplexity

[direct link]

word-emb-size

[direct link]