Michael Röder

@wouterbeek Thanks a lot. Very interesting service :+1:

Dataset info page: https://catalog.ldc.upenn.edu/LDC2006T06 From my point of view we would need a "LDC User Agreement for Non-Members" Example: https://catalog.ldc.upenn.edu/desc/addenda/LDC2006T06.txt

Okay. However, Let's make sure that we can use the dataset. It contains a lot of markings, e.g., relations, dates and pronouns. Just take a look at the example and...

Thanks for that question. I can only give a general answer since you have uploaded a larger dataset. I think uploading an example with a single document for which the...

@jplu thanks for this example. Going through it manually, I have calculated the same result as the `nel-eval` script. |GS start | GS length | GS URI | GS type...

@TortugaAttack I have reproduced the problem using the two [NIF files listed above](https://github.com/dice-group/gerbil/issues/226#issuecomment-347273225). You can use the [FileBasedNIFDataset](https://github.com/dice-group/gerbil/blob/master/src/main/java/org/aksw/gerbil/dataset/impl/nif/FileBasedNIFDataset.java) for loading the data and the [InstanceListBasedAnnotator](https://github.com/dice-group/gerbil/blob/master/src/main/java/org/aksw/gerbil/annotator/impl/instance/InstanceListBasedAnnotator.java) to load the result file...

I do not see how this solves the issue since we have to count it as a false positive - as it is done in the [table above](https://github.com/dice-group/gerbil/issues/226#issuecomment-347527331) as well....

The table is structured by the gold std. entities (11) and the entities of the system answers (12) mapped to them. The last system answer does not match any gold...

1. We fixed a bug in the hierarchical F1-measure counting that could lead to doubling the number of fp counts. 2. Apart from that, there is a misunderstanding in the...

Of cause, we will let you know. However, I think we still have a small misunderstanding. Let's focus on the "Paris" / "Paris)" example. I totally agree that the recognition...