Sciweavers

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

5

COLING
2008

favoriteEmaildiscussreport

108views Computational Linguistics» more COLING 2008»

Source Language Markers in EUROPARL Translations

13 years 6 months ago

Source Language Markers in EUROPARL Translations

Download www.aclweb.org

This paper shows that it is very often possible to identify the source language of medium-length speeches in the EUROPARL corpus on the basis of frequency counts of word n-grams (87.2%96.7% accuracy depending on classification method). The paper also examines in detail which positive markers are most powerful and identifies a number of linguistic aspects as well as culture- and domain-related ones.1

Hans van Halteren

Real-time Traffic

COLING 2008 | Computational Linguistics | Frequency Counts | Medium-length Speeches | Word N-grams |

claim paper

Related Content

» OpenMaTrEx A FreeOpenSource MarkerDriven ExampleBased Machine Translation System

» A Comparison of Pivot Methods for PhraseBased Statistical Machine Translation

» Semisupervised model adaptation for statistical machine translation

» Sinuhe Statistical Machine Translation using a Globally Trained Conditional Exponential F...

» Evaluation of a Machine Translation System for Low Resource Languages METISII

» Combining Morphemebased Machine Translation with Postprocessing Morpheme Prediction

» Learning to Predict Case Markers in Japanese

» Automatic Inference of the Temporal Location of Situations in Chinese Text

Post Info
More Details (n/a)

Added	29 Oct 2010
Updated	29 Oct 2010
Type	Conference
Year	2008
Where	COLING
Authors	Hans van Halteren

Comments (0)