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.

Git repo URL: git://gonito.net/retro-gap.git / Branch: master

(Browse at https://gonito.net/gitlist/retro-gap.git/master)

Leaderboard

# submitter when description test-A/LogLossHashed ×
1 kaczla 2017-12-12 20:35 3-gram with prune, best 15, best oov ready-made kenlm lm 5.7006 20
2 siulkilulki 2018-01-24 14:39 simple neural network, context 2 words ahead 2 words behind neural-network 5.7395 4
3 p/tlen 2018-01-03 06:07 a very simple (non-recurrent) neural network, looking one word behind and one word ahead (train on all data), dictionary size=40000 neural-network 5.8648 4
4 tamazaki 2017-04-24 16:42 unigramy, n=100, v3 self-made lm 6.0733 4
5 patrycja 2018-01-15 18:11 Bigrams model, 100 best words self-made lm bigram stupid 6.1097 1
6 mmalisz 2017-06-29 15:12 Update source code; kenlm order=3 tokenizer.perl from moses. best 100 results, text mode. lm kenlm ready-made 6.1898 5
7 EmEm 2017-05-16 04:31 zad 16 self-made lm 6.8056 3
8 Durson 2017-06-28 08:47 test 2 ready-made neural-network 6.8956 2