kubapok
/
twittersentiment140-sentiment-word-gap-clean
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
3 Commits 1 Branch 0 Tags 59 MiB
Python 97%
Shell 3%
Go to file
kubapok d9af20c013 rename train 2021-11-11 10:52:26 +01:00
dev-0 init 2021-11-01 19:46:45 +01:00
just_roberta_base inference on cuda 2021-11-11 10:49:15 +01:00
regular_roberta_from_scratch inference on cuda 2021-11-11 10:49:15 +01:00
roberta_ft inference on cuda 2021-11-11 10:49:15 +01:00
roberta_with_year_from_scratch inference on cuda 2021-11-11 10:49:15 +01:00
roberta_with_year_ft inference on cuda 2021-11-11 10:49:15 +01:00
test-A init 2021-11-01 19:46:45 +01:00
train rename train 2021-11-11 10:52:26 +01:00
.gitignore init 2021-11-01 19:46:45 +01:00
README.md init 2021-11-01 19:46:45 +01:00
config.txt init 2021-11-01 19:46:45 +01:00
how_to_run inference on cuda 2021-11-11 10:49:15 +01:00

README.md

twitter 140 temporal word gap filling

Dataset from paper "Twitter Sentiment Classification using Distant Supervision"

Dev test contains 100k samples from train set. Test set has deleted neutral samples and added 100k samples from train set.

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