Go to file

Jakub Pokrywka aa3244ca2b hf linear layer, roberta challam finetunned firstly on roberta challam year prediction, then on wiki historian		2022-07-18 20:18:08 +00:00
challam_year_prediction_on_challam_model	hf linear layer, roberta challam finetunned firstly on roberta challam year prediction, then on wiki historian	2022-07-18 20:18:08 +00:00
dev-0	hf linear layer, roberta challam finetunned firstly on roberta challam year prediction, then on wiki historian	2022-07-18 20:18:08 +00:00
hf_roberta_base	hf roberta challam regression layer on top	2022-07-14 19:19:12 +00:00
mean_from_train	mean from train	2022-02-12 19:46:31 +01:00
test-A	hf linear layer, roberta challam finetunned firstly on roberta challam year prediction, then on wiki historian	2022-07-18 20:18:08 +00:00
train	init	2022-02-12 19:14:40 +01:00
.gitignore	init	2022-02-12 19:14:40 +01:00
config.txt	init	2022-02-12 19:14:40 +01:00
in-header.tsv	init	2022-02-12 19:14:40 +01:00
out-header.tsv	init	2022-02-12 19:14:40 +01:00
README.md	change name	2022-02-12 19:30:51 +01:00

README.md

Wiki Historian En

Guess the masked date in an wikipedia article.

Only dates 1835-1935 are considered.

You should predict only one masked date in an article described as [DATEPREDICT]. [DATEMASK] are other masked dates. The predicted date should be in fractional year format.

Fractional year format:

Year is normalized as follows:

''' days_in_year = 366 if is_leap else 365 normalized = d.year + ((day_of_year-1) / days_in_year) '''

Directory structure

README.md — this file
config.txt — configuration file
train/ — directory with training data
train/in.tsv — input data for the train set
train/expected.tsv — expected (reference) data for the train set
dev-0/ — directory with dev (test) data
dev-0/in.tsv — input data for the dev set
dev-0/expected.tsv — expected (reference) data for the dev set
test-A — directory with test data
test-A/in.tsv — input data for the test set
test-A/expected.tsv — expected (reference) data for the test set