Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

10

EACL
2003
ACL Anthology

favoriteEmaildiscussreport

141views Natural Language Processing» more EACL 2003»

Empirical Methods for Compound Splitting

13 years 6 months ago

Empirical Methods for Compound Splitting

Download www.iccs.informatics.ed.ac.uk

Compounded words are a challenge for NLP applications such as machine translation (MT). We introduce methods to learn splitting rules from monolingual and parallel corpora. We evaluate them against a gold standard and measure their impact on performance of statistical MT systems. Results show accuracy of 99.1% and performance gains for MT of 0.039 BLEU on a German-English noun phrase translation task.

Philipp Koehn, Kevin Knight

Real-time Traffic

EACL 2003 | German-English Noun Phrase | Natural Language Processing | Parallel Corpora | Statistical Mt Systems |

claim paper

Related Content

» Unsupervised and KnowledgeFree Learning of Compound Splits and Periphrases

» Statistical Machine Translation of German Compound Words

» Comparing Simplification Methods for Model Trees with Regression and Splitting Nodes

» FAFDrugs2 Free ADMEtox filtering tool to assist drug discovery and chemical biology projec...

» Analysis of approximate nearest neighbor searching with clustered point sets

» Random Ordinality Ensembles A Novel Ensemble Method for Multivalued Categorical Data

» Improved Algorithms for Univariate Discretization of Continuous Features

» Estimating the Location and Orientation of Complex Correlated Neural Activity using MEG

» Linguistically Motivated Unsupervised Segmentation for Machine Translation

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2003
Where	EACL
Authors	Philipp Koehn, Kevin Knight

Comments (0)