@prefix dc: <http://purl.org/dc/terms/> .
@prefix this: <http://purl.org/np/RAZPEGFmvTb0KxdfMKih1ZhI_jYquGyBI4hyO_wuL_org> .
@prefix sub: <http://purl.org/np/RAZPEGFmvTb0KxdfMKih1ZhI_jYquGyBI4hyO_wuL_org#> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
@prefix prov: <http://www.w3.org/ns/prov#> .
@prefix pav: <http://purl.org/pav/> .
@prefix np: <http://www.nanopub.org/nschema#> .
@prefix linkflows: <https://github.com/LaraHack/linkflows_model/blob/master/Linkflows.ttl#> .
sub:Head {
  this: np:hasAssertion sub:assertion ;
    np:hasProvenance sub:provenance ;
    np:hasPublicationInfo sub:pubinfo ;
    a np:Nanopublication .
}
sub:assertion {
  sub:comment-10 a linkflows:ActionNeededComment , linkflows:ContentComment , linkflows:NegativeComment , linkflows:ReviewComment ;
    linkflows:hasCommentText "* The experimental settings include a rather simple strategy for seed selection (for both training the frame/FE classifiers and selecting the sentences to be used for extracting assertions in the first place), viz., sentence filtering according to a maximum length of words. First, for the sake of exactness and replicability of the results, this threshold should be explicitly stated. Second, I am a bit concerned that this strategy might introduce a bias towards shorter sentence with a relatively simple syntactic structure, which might explain why Named Entity Linking serves well as a surrogate of syntactic parsing. If so, this clearly questions the scalability of the approach. In any case, I would like to see a more comprehensive discussion of these aspects." ;
    linkflows:hasImpact "3"^^xsd:positiveInteger ;
    linkflows:refersTo <http://purl.org/np/RAY-P-WxUizJ4zp5oqi4g_VhexHS1B6U_521yTLvWOmec#section> .
}
sub:provenance {
  sub:assertion prov:hadPrimarySource <http://dx.doi.org/10.3233/SW-170269> ;
    prov:wasAttributedTo <https://orcid.org/0000-0001-6549-066X> .
}
sub:pubinfo {
  this: dc:created "2019-11-26T09:05:11+01:00"^^xsd:dateTime ;
    pav:createdBy <https://orcid.org/0000-0002-7114-6459> .
}