Joint training of dependency parsing filters through latent support vector machines

Download
  1. (PDF, 333 KB)
AuthorSearch for: ; Search for:
TypeArticle
Proceedings titleProceedings of the 49th Annual Meeting of the Association for Computational Linguistics: shortpapers
ConferenceThe 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL HLT 2011), June 19-24, 2011, Portland, Oregon, USA
Pages200205; # of pages: 6
AbstractGraph-based dependency parsing can be sped up significantly if implausible arcs are eliminated from the search-space before parsing begins. State-of-the-art methods for arc filtering use separate classifiers to make pointwise decisions about the tree; they label tokens with roles such as root, leaf, or attaches-to-the- left, and then filter arcs accordingly. Because these classifiers overlap substantially in their filtering consequences, we propose to train them jointly, so that each classifier can focus on the gaps of the others. We integrate the various pointwise decisions as latent variables in a single arc-level SVM classifier. This novel framework allows us to combine nine pointwise filters, and adjust their sensitivity using a shared threshold based on arc length. Our system filters 32% more arcs than the independently-trained classifiers, without reducing filtering speed. This leads to faster parsing with no reduction in accuracy.
Publication date
LanguageEnglish
AffiliationNRC Institute for Information Technology; National Research Council Canada
Peer reviewedNo
NPARC number18533388
Export citationExport as RIS
Report a correctionReport a correction
Record identifier27cad092-0e19-4e99-98a2-54534e60fe54
Record created2011-09-07
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)