Aaron Jaech

I think you are looking in the wrong file for the cluster output. Look for a file called "paths" for the cluster ids.

The size of the input data doesn't matter as much as the size of the vocabulary. How big is the vocabulary you are dealing with?

I'm not sure what the exact limit is but I'm not surprised that it failed with 20M types. You can try using the restrict command line option to restrict it...

Did you try using the flag to restrict the vocabulary? On Thursday, July 14, 2016, lavelli [email protected] wrote: > I have noticed that at the end of March a new...

That looks like a mistake. Thanks for finding it. I don't think it effects anything though.

Hi, can you email me at [email protected] and I will help you get started using the code and data.

If you email me at [email protected] I can help you get started with the data.