Conversation

Notices

1. Allison Parrish (aparrish@mastodon.social)'s status on Wednesday, 20-Jun-2018 12:57:11 EDT Allison Parrish

   output from a convolutional neural network trying to "condense" wikipedia articles about each of zukofsky's 80 Flowers into the text of the poems themselves. the first is from a word-level model, attempting to produce one of the poems in the validation set; the second is from a character-level model, trying to produce one of the poems in the training set. the word-level one looks "coherent" but it's really just reproducing words in similar frequencies from the targets

   1. Allison Parrish (aparrish@mastodon.social)'s status on Wednesday, 20-Jun-2018 13:01:10 EDT Allison Parrish

      in reply to

      in both cases there's so little data (just 80 items, since there are just 80 poems...) that the model pretty much instantly overfits and basically just learns the poems verbatim. I think I'm going to go back to the word model and try using pre-trained embeddings, then investigate data augmentation? (but allison, you're saying, CNN is very inappropriate for this task, use LSTM, bleah, and yes I know but I have Something I'm Trying To Show about zukofsky's style of composition in these poems)