John Bauer

Is this a long list of people and places? The NER expects context in a sentence, not a list of names, so it will not function well on an example...

I guess it should be able to recognize General Mills but doesn't. Maybe it's not in the training data. I also notice that your periods are being tokenized with the...

I'm sorry, but we no longer distribute that annotator. On Tue, Dec 24, 2019 at 5:07 PM cklsoft wrote: > Hi, I've seen NFLAnnotator.java in > src/edu/stanford/nlp/pipeline/package-info.java but I can...

I think it's just out of date. Better results from kbp and/or openie On Tue, Dec 24, 2019 at 6:13 PM cklsoft wrote: > er distribute that annotator. > >...

Ok, it's true that if you want to process 33-yard and get an annotation that's a distance we currently don't have an annotator for that. However, you can probably use...

The statistical model doesn't have any experience recognizing that particular date format. If you run CoreNLP with only the models you can see that it doesn't recognize it there, either:...

What happens if you add back the l1reg? That should force weights to 0, which should reduce the size of the final model. Also, I retrained the model recently on...

Ah, that's a good point. I'll check with our PI to see if things have changed in terms of what we can publicly release. On Mon, Jan 20, 2020 at...

Sorry (again) for the late reply. What should work is the parameters useQN=true useOWLQN=true priorLambda= (some hyperparameter)

As far as I can tell, what you are trying to do is not the intended use of boundaryMultiTokenRegex. The documentation says "The matched tokens will be treated as not...