Andrea Giovanni Nuzzolese
Andrea Giovanni Nuzzolese
> Yes, indeed, clear ... for you @anuzzolese :-) The evaluation dataset is shaped as the training dataset in terms of the nature and the number of sentences. Your system...
@lara-hdr Basically, the input consists of set of couples . This input is represented by using RDF with the NIF notation. For example, look at https://github.com/anuzzolese/oke-challenge-2016/blob/master/example_data/task2.ttl for more details.
It is correct.
The Web API has to be designed in order to handle one sentence to be annotated per request. Hence, the API is expected to provide as output the NIF annotation...
An entity can have multiple types in the goldstandard. A system should provide at least one correct type for an entity. However, all wrong types returned by a system for...
Hi @Flutifioc, the correct type is d0:Location. dul:Location is a typo in the dataset. This has been fixed (cf. commit 8d36370).
Dear Giuseppe, we used DBpedia 2014. Andrea
Dear @rtroncy, the training set is composed of the data available from last year when we used dbpedia2014 (i.e., http://dbpedia.org/Downloads2014) as reference DBpedia release. Nevertheless, we verified that all the...
Did you install the package with pip?
Hi @henrieglesorotos, if i got the problem you are referring to correctly I would say that it is somehow implemented (maybe not the best solution, but we can discuss about...