Publication:
Piecewise Pseudolikelihood for Efficient Training of Conditional Random Fields

Simple item page
dc.contributor.authorSutton, Charles
dc.contributor.authorMcCallum, Andrew
dc.contributor.departmentUniversity of Massachusetts - Amherst
dc.contributor.departmentUniversity of Massachusetts - Amherst
dc.date2023-09-22T21:09:52.000
dc.date.accessioned2024-04-26T09:36:57Z
dc.date.available2024-04-26T09:36:57Z
dc.date.issued2007-01-01
dc.descriptionThis paper was harvested from CiteSeer
dc.description.abstractDiscriminative training of graphical models can be expensive if the variables have large cardinality, even if the graphical structure is tractable. In such cases, pseudolikelihood is an attractive alternative, because its running time is linear in the variable cardinality, but on some data its accuracy can be poor. Piecewise training (Sutton & McCallum, 2005) can have better accuracy but does not scale as well in the variable cardinality. In this paper, we introduce piecewise pseudolikelihood, which retains the computational efficiency of pseudolikelihood but can have much better accuracy. On several benchmark NLP data sets, piecewise pseudolikelihood has better accuracy than standard pseudolikelihood, and in many cases nearly equivalent to maximum likelihood, with five to ten times less training time than batch CRF training.
dc.identifier.urihttps://hdl.handle.net/20.500.14394/10237
dc.relation.urlhttps://scholarworks.umass.edu/cgi/viewcontent.cgi?article=1064&context=cs_faculty_pubs&unstamped=1
dc.source.statuspublished
dc.subjectComputer Sciences
dc.titlePiecewise Pseudolikelihood for Efficient Training of Conditional Random Fields
dc.typearticle
dc.typearticle
digcom.contributor.authorSutton, Charles
digcom.contributor.authorMcCallum, Andrew
digcom.identifiercs_faculty_pubs/62
digcom.identifier.contextkey1300661
digcom.identifier.submissionpathcs_faculty_pubs/62
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Charles_Sutton.pdf
Size:
220.42 KB
Format:
Adobe Portable Document Format
Thumbnail Image
Name: Charles_Sutton.pdf
Size: 220.42 KB
Kind: Adobe PDF
Collections
Computer Science Department Faculty Publication Series