structured-neural-summarization
structured-neural-summarization copied to clipboard
CoderPat
A repository with the code for the paper with the same title
I used Stanford's processing tool to process the original text into xml format, which does not contain the "headline" tag, and the code directly skips files without "headline". Can you...
I am trying to validate your model with a method-naming task in Java-small. Therefore, I converted the source code into a graph representation using Java2Graph code. However, I didn't find...
Since I don't know the structure of your data set, I can't understand your experiment better. Can you give me your data set?
I see quite often the following error. See below for a stack trace (ignore the line numbers, I have a local copy of the code that has debug prints, more...
Hi, When I follow the instructions to get the used format about C# docstring data and I find there are no samples contain the key 'Summary' in your script programgraphs2opengnn.py....
When I running the train_and_eval.py on CNNDailyMail dataset, it often has the problem'UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of...
Thank you very much for providing the latest updates to the repo. I am still having trouble training the model on a small subset of CNNDailymail data. Upon inferencing, the...
hello，ognn-build-vocab --with_sequence_tokens \ --save_vocab /data/naturallanguage/cnn_dailymail/output.vocab \ /data/naturallanguage/cnn_dailymail/split/train/targets.jsonl.gz Is 'targets.jsonl.gz' mentioned here 'summaries.jsonl.gz'? I am running this line of code: python convert2graph.py /path/to/output/xml /path/to/summaries /path/to/output I got the 'inputs.jsonl.gz' and 'summaries.jsonl.gz',There...
I described the issue in the PR that "fixes" it #8 There are problems after removing labels in running the code as is (to fix, labels needs to be remove...
Based on a discussion in https://github.com/CoderPat/structured-neural-summarization/issues/10 `train_and_eval` should be run with `case_sensitive=False`. It is by default false, so `case_sensitive` should be removed from the run scripts in `models`.