Matches in SemOpenAlex for { <https://semopenalex.org/work/W2287663210> ?p ?o ?g. }
- W2287663210 endingPage "486" @default.
- W2287663210 startingPage "465" @default.
- W2287663210 abstract "Structured learning algorithms usually require inference during the training procedure. Due to their exponential size of output space, the parameter update is performed only on a relatively small collection built from the ?best? structures. The k-best MIRA is an example of an online algorithm which seeks optimal parameters by making updates on k structures with the highest score at a time. Following the idea of using k-best structures during the learning process, in this paper we introduce four new k-best extensions of max-margin structured algorithms. We discuss their properties and connection, and evaluate all algorithms on two sequence labeling problems, the shallow parsing and named entity recognition. The experiments show how the proposed algorithms are affected by the changes of k in terms of the F-measure and computational time, and that the proposed algorithms can improve results in comparison to the single best case. Moreover, the restriction to the single best case produces a comparison of the existing algorithms." @default.
- W2287663210 created "2016-06-24" @default.
- W2287663210 creator A5003822198 @default.
- W2287663210 creator A5056053837 @default.
- W2287663210 date "2015-01-01" @default.
- W2287663210 modified "2023-10-16" @default.
- W2287663210 title "K-best max-margin approaches for sequence labeling" @default.
- W2287663210 cites W1512098439 @default.
- W2287663210 cites W1714704734 @default.
- W2287663210 cites W1893264043 @default.
- W2287663210 cites W1934019294 @default.
- W2287663210 cites W1979711143 @default.
- W2287663210 cites W1997644175 @default.
- W2287663210 cites W2000130940 @default.
- W2287663210 cites W2004048363 @default.
- W2287663210 cites W2008652694 @default.
- W2287663210 cites W2009593947 @default.
- W2287663210 cites W2031248101 @default.
- W2287663210 cites W2036102925 @default.
- W2287663210 cites W2084413241 @default.
- W2287663210 cites W2097826433 @default.
- W2287663210 cites W2098921539 @default.
- W2287663210 cites W2105644991 @default.
- W2287663210 cites W2105842272 @default.
- W2287663210 cites W2112865076 @default.
- W2287663210 cites W2116410915 @default.
- W2287663210 cites W2125838338 @default.
- W2287663210 cites W2125993116 @default.
- W2287663210 cites W2135106139 @default.
- W2287663210 cites W2139686264 @default.
- W2287663210 cites W2147880316 @default.
- W2287663210 cites W2148603752 @default.
- W2287663210 cites W2160218441 @default.
- W2287663210 cites W2181464929 @default.
- W2287663210 cites W2407980920 @default.
- W2287663210 cites W2798766386 @default.
- W2287663210 cites W2964262905 @default.
- W2287663210 doi "https://doi.org/10.2298/csis140713014m" @default.
- W2287663210 hasPublicationYear "2015" @default.
- W2287663210 type Work @default.
- W2287663210 sameAs 2287663210 @default.
- W2287663210 citedByCount "0" @default.
- W2287663210 crossrefType "journal-article" @default.
- W2287663210 hasAuthorship W2287663210A5003822198 @default.
- W2287663210 hasAuthorship W2287663210A5056053837 @default.
- W2287663210 hasBestOaLocation W22876632101 @default.
- W2287663210 hasConcept C111919701 @default.
- W2287663210 hasConcept C11413529 @default.
- W2287663210 hasConcept C119857082 @default.
- W2287663210 hasConcept C124101348 @default.
- W2287663210 hasConcept C13355873 @default.
- W2287663210 hasConcept C154945302 @default.
- W2287663210 hasConcept C186644900 @default.
- W2287663210 hasConcept C22367795 @default.
- W2287663210 hasConcept C2524010 @default.
- W2287663210 hasConcept C2776214188 @default.
- W2287663210 hasConcept C2778112365 @default.
- W2287663210 hasConcept C2780009758 @default.
- W2287663210 hasConcept C33923547 @default.
- W2287663210 hasConcept C41008148 @default.
- W2287663210 hasConcept C54355233 @default.
- W2287663210 hasConcept C774472 @default.
- W2287663210 hasConcept C80444323 @default.
- W2287663210 hasConcept C86803240 @default.
- W2287663210 hasConcept C98045186 @default.
- W2287663210 hasConceptScore W2287663210C111919701 @default.
- W2287663210 hasConceptScore W2287663210C11413529 @default.
- W2287663210 hasConceptScore W2287663210C119857082 @default.
- W2287663210 hasConceptScore W2287663210C124101348 @default.
- W2287663210 hasConceptScore W2287663210C13355873 @default.
- W2287663210 hasConceptScore W2287663210C154945302 @default.
- W2287663210 hasConceptScore W2287663210C186644900 @default.
- W2287663210 hasConceptScore W2287663210C22367795 @default.
- W2287663210 hasConceptScore W2287663210C2524010 @default.
- W2287663210 hasConceptScore W2287663210C2776214188 @default.
- W2287663210 hasConceptScore W2287663210C2778112365 @default.
- W2287663210 hasConceptScore W2287663210C2780009758 @default.
- W2287663210 hasConceptScore W2287663210C33923547 @default.
- W2287663210 hasConceptScore W2287663210C41008148 @default.
- W2287663210 hasConceptScore W2287663210C54355233 @default.
- W2287663210 hasConceptScore W2287663210C774472 @default.
- W2287663210 hasConceptScore W2287663210C80444323 @default.
- W2287663210 hasConceptScore W2287663210C86803240 @default.
- W2287663210 hasConceptScore W2287663210C98045186 @default.
- W2287663210 hasFunder F4320322729 @default.
- W2287663210 hasIssue "2" @default.
- W2287663210 hasLocation W22876632101 @default.
- W2287663210 hasOpenAccess W2287663210 @default.
- W2287663210 hasPrimaryLocation W22876632101 @default.
- W2287663210 hasRelatedWork W1580210754 @default.
- W2287663210 hasRelatedWork W2111753845 @default.
- W2287663210 hasRelatedWork W2251302701 @default.
- W2287663210 hasRelatedWork W2752432813 @default.
- W2287663210 hasRelatedWork W2953238046 @default.
- W2287663210 hasRelatedWork W2963058055 @default.
- W2287663210 hasRelatedWork W4225307033 @default.
- W2287663210 hasRelatedWork W4300631627 @default.
- W2287663210 hasRelatedWork W4301170185 @default.