open-sesame
open-sesame copied to clipboard
swabhs
A frame-semantic parsing system based on a softmax-margin SegRNN.
I am trying to train the frameid model, but I get this error at the very beginning of training. I am using the latest version of dynet (2.1). I have...
Hello, I tried to train new models from scratch, but that wouldn't work. The targetid training would go fine, but then frameid would halt with a NaN error. It would...
This PR fixes a bug in the preprocess step for Python 3, which is writing tokens as `b'token'` instead of just `token`, as pointed out in @appleternity in https://github.com/swabhs/open-sesame/issues/61#issuecomment-789312514. [Python...
- fixed broken download link for the embeddings - fixed correct folder name (`$DATA` instead of `$DATA/embeddings_glove`) for the folder the embedding file needs to be extracted to as otherwise...
When I try to annotate the frames from the targets.conll file: I get a "Killed" message (Last line): The input text file is 178MB. The `predicted_targets.conll` file is about 11GB....
In the second step: ``` Second, this project uses pretrained GloVe word embeddings of 100 dimensions, trained on 6B tokens. Download and extract under $DATA/embeddings_glove/. ``` The link to glove...
I recently provided openSesame a **4MB** text file. The _predicted_args.conll_ was about **260MB**, and took about 1 complete day (24hours) to annotate entirely. I now have a **300MB** text file...
Dimensions of lookup parameter /_0 lookup up from file ({100,400574}) do not match parameters to be populated ({100,410050})
