gregdurrett / berkeley-doc-summarizer Goto Github PK

Hi @gregdurrett

I am currently using the Entity Preprocessing Driver main method to turn my regular .txt files into the (Conll?) format understood by this summarizer however I am getting issues at the moment with the ConllReader class used in the Summarizer class unable to parse some of the generated lines (in the assembleConstTree method because some lines appear to be missing a "*")

Would you be able to shed more light on the Conll format that the summarizer is expecting?

Thanks,
Harry

Your instructions mention:

To prepare the dataset, first you need to extract all the XML files from 2003-2007 and flatten them into a single directory

Is 2003-2007 referring to train_corefner_standoff or train_abstracts_standoff?

Within each of these directories, the files contained don't seem to have an XML format.

Not sure how to do the aforementioned step...

Kindly share a demo link of your project. I would like to test the summarization. Please let me know where I can get to see your project demo.
Thank you in advance.

Hi,

I am trying to use your summarizer and refer your paper in my paper, but I got an exception as the following:

I am using mac os. I am trying to set java jni but I always got an error. There will be /usr/local/lib/jni in mac os wrote in the readme, but I can't find any folder with jni in my mac. Could you please tell me how to set jni with mac? I appreciate your help. Thank you.

Thanks for your code sharing. Can you tell me what should I put into train_corefner_standoff and train_abstracts_standoff directory?

The joint model (COREF+NER+WIKI) of the Berkeley Entity Resolution System combines the output for all input documents (e.g. government.txt and music.txt) into a single file output.conll.
While the output produced by other models does not exactly match the test files in the Berkeley Document Summarizer (e.g. the last two columns of government.txt are off).
Would appreciate a clarification on the assumed data interface between the Berkeley Entity Resolution System and the Berkeley Document Summarizer.