Matches in UGent Biblio for { <https://biblio.ugent.be/publication/598362#aggregation> ?p ?o. }
Showing items 1 to 38 of
38
with 100 items per page.
- aggregation classification "P1".
- aggregation creator B83019.
- aggregation creator B83020.
- aggregation creator B83021.
- aggregation creator B83022.
- aggregation creator B83023.
- aggregation creator B83024.
- aggregation creator B83025.
- aggregation creator B83026.
- aggregation creator person.
- aggregation date "2008".
- aggregation format "application/pdf".
- aggregation hasFormat 598362.bibtex.
- aggregation hasFormat 598362.csv.
- aggregation hasFormat 598362.dc.
- aggregation hasFormat 598362.didl.
- aggregation hasFormat 598362.doc.
- aggregation hasFormat 598362.json.
- aggregation hasFormat 598362.mets.
- aggregation hasFormat 598362.mods.
- aggregation hasFormat 598362.rdf.
- aggregation hasFormat 598362.ris.
- aggregation hasFormat 598362.txt.
- aggregation hasFormat 598362.xls.
- aggregation hasFormat 598362.yaml.
- aggregation isPartOf urn:isbn:9782951740846.
- aggregation language "eng".
- aggregation publisher "European Language Resources Association (ELRA)".
- aggregation rights "I have transferred the copyright for this publication to the publisher".
- aggregation subject "Languages and Literatures".
- aggregation title "A coreference corpus and resolution system for Dutch".
- aggregation abstract "We present the main outcomes of the COREA project: a corpus annotated with coreferential relations and a coreference resolution system for Dutch. In the project we developed annotation guidelines for coreference resolution for Dutch and annotated a corpus of 135K tokens. We discuss these guidelines, the annotation tool, and the inter-annotator agreement. We also show a visualization of the annotated relations. The standard approach to evaluate a coreference resolution system is to compare the predictions of the system to a hand-annotated gold standard test set (cross-validation). A more practically oriented evaluation is to test the usefulness of coreference relation information in an NLP application. We run experiments with an Information Extraction module for the medical domain, and measure the performance of this module with and without the coreference relation information. We present the results of both this application-oriented evaluation of our system and of a standard cross-validation evaluation. In a separate experiment we also evaluate the effect of coreference information produced by a simple rule-based coreference module in a Question Answering application.".
- aggregation authorList BK213411.
- aggregation endPage "149".
- aggregation startPage "144".
- aggregation aggregates 601405.
- aggregation isDescribedBy 598362.
- aggregation similarTo LU-598362.