Greg Durrett

Hi Joe, Look in edu.berkeley.nlp.entity.coref.CorefDocAssembler. extractPredMentions is the method you want. Let me know if you have other questions. Greg On Mon, Sep 28, 2015 at 10:24 PM, Joe Cheri...

Hi Joe, Please re-ping me about this early next week, I'm traveling and and dealing with a bunch of other stuff right now so I'm afraid I'm going to forget...

Hi Harry, Glad you figured out the first issue -- guess that should be documented... The no gold mentions warning is normal -- basically this isn't gold coreference data so...

This is probably because the "input sentence" is actually several sentences. It needs to be split further for the parser to do the right thing. BTW I don't really maintain...

Does that directory exist? GUtil is trying to open the file for write and can't do it, and that's the main reason that might happen. Greg On Sat, Dec 26,...

Yep, that's definitely wrong...I must have never noticed because I write models to the current directory so the parent ends up being null.

(A PR would be nice, thanks!)

This used to be available here: http://nlp.cs.berkeley.edu/projects/summarizer.shtml but unfortunately the files are gone. I am unfortunately unable to maintain this repo anymore. My PhD student Jiacheng Xu has a similar...

(putting this here as well for others who have this issue) I'm not sure what the exact issue is. I assume you followed the directions on http://glpk-java.sourceforge.net/index.html#Downloading for downloading and...

Yes, that should be the case. Note that i is the index of the current mention and j is the index of the antecedent (so j < i, with j...