This HTML5 document contains 42 embedded RDF statements represented using HTML+Microdata notation.

The embedded RDF content will be recognized by any processor of HTML5 Microdata.

Namespace Prefixes

PrefixIRI
n4http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n15http://localhost/temp/predkladatel/
n11http://purl.org/net/nknouf/ns/bibtex#
n16http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n12http://linked.opendata.cz/ontology/domain/vavai/
n14https://schema.org/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n3http://linked.opendata.cz/ontology/domain/vavai/riv/
n9http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F00216208%3A11320%2F14%3A10289359%21RIV15-MSM-11320___/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n5http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n13http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n19http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n18http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n20http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n17http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n7http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F00216208%3A11320%2F14%3A10289359%21RIV15-MSM-11320___
rdf:type
n12:Vysledek skos:Concept
dcterms:description
This paper describes Parmesan, our submission to the 2014 Workshop on Statistical Machine Translation (WMT) metrics task for evaluation English-to-Czech translation. We show that the Czech Meteor Paraphrase tables are so noisy that they actually can harm the performance of the metric. However, they can be very useful after extensive filtering in targeted paraphrasing of Czech reference sentences prior to the evaluation. Parmesan first performs targeted paraphrasing of reference sentences, then it computes the Meteor score using only the exact match on~these new reference sentences. It shows significantly higher correlation with human judgment than Meteor on the WMT12 and WMT13 data. This paper describes Parmesan, our submission to the 2014 Workshop on Statistical Machine Translation (WMT) metrics task for evaluation English-to-Czech translation. We show that the Czech Meteor Paraphrase tables are so noisy that they actually can harm the performance of the metric. However, they can be very useful after extensive filtering in targeted paraphrasing of Czech reference sentences prior to the evaluation. Parmesan first performs targeted paraphrasing of reference sentences, then it computes the Meteor score using only the exact match on~these new reference sentences. It shows significantly higher correlation with human judgment than Meteor on the WMT12 and WMT13 data.
dcterms:title
Parmesan: Meteor without Paraphrases with Paraphrased References Parmesan: Meteor without Paraphrases with Paraphrased References
skos:prefLabel
Parmesan: Meteor without Paraphrases with Paraphrased References Parmesan: Meteor without Paraphrases with Paraphrased References
skos:notation
RIV/00216208:11320/14:10289359!RIV15-MSM-11320___
n3:aktivita
n18:S
n3:aktivity
S
n3:dodaniDat
n7:2015
n3:domaciTvurceVysledku
n16:3166732
n3:druhVysledku
n20:D
n3:duvernostUdaju
n13:S
n3:entitaPredkladatele
n9:predkladatel
n3:idSjednocenehoVysledku
35794
n3:idVysledku
RIV/00216208:11320/14:10289359
n3:jazykVysledku
n19:eng
n3:klicovaSlova
references; paraphrased; with; paraphrases; without; meteor; parmesan
n3:klicoveSlovo
n5:parmesan n5:meteor n5:references n5:with n5:without n5:paraphrased n5:paraphrases
n3:kontrolniKodProRIV
[9C58626B04F5]
n3:mistoKonaniAkce
Baltimore, MD, USA
n3:mistoVydani
Baltimore, MD, USA
n3:nazevZdroje
Proceedings of the Ninth Workshop on Statistical Machine Translation
n3:obor
n17:IN
n3:pocetDomacichTvurcuVysledku
1
n3:pocetTvurcuVysledku
1
n3:rokUplatneniVysledku
n7:2014
n3:tvurceVysledku
Barančíková, Petra
n3:typAkce
n4:WRD
n3:zahajeniAkce
2014-06-26+02:00
s:numberOfPages
7
n11:hasPublisher
Association for Computational Linguistics
n14:isbn
978-1-941643-17-4
n15:organizacniJednotka
11320