Sciweavers

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

9

ACL
2012

favoriteEmaildiscussreport

158views Computational Linguistics» more ACL 2012»

A Statistical Model for Unsupervised and Semi-supervised Transliteration Mining

11 years 6 months ago

A Statistical Model for Unsupervised and Semi-supervised Transliteration Mining

Download www.ims.uni-stuttgart.de

We propose a novel model to automatically extract transliteration pairs from parallel corpora. Our model is efﬁcient, language pair independent and mines transliteration pairs in a consistent fashion in both unsupervised and semi-supervised settings. We model transliteration mining as an interpolation of transliteration and non-transliteration sub-models. We evaluate on NEWS 2010 shared task data and on parallel corpora with competitive results.

Hassan Sajjad, Alexander Fraser, Helmut Schmid

Real-time Traffic

ACL 2012 | Computational Linguistics | Consistent Fashion | Parallel Corpora | Supervised Settings |

claim paper

Related Content

» Aspect Extraction through SemiSupervised Modeling

» A General Model for Multiple View Unsupervised Learning

» Unsupervised modeling of object categories using link analysis techniques

» Discovery of Term Variation in Japanese Web Search Queries

» Unsupervised query segmentation using only query logs

» Mining contrastive opinions on political texts using crossperspective topic model

» Mining InternetScale Software Repositories

» Sparse Word Graphs A Scalable Algorithm for Capturing Word Correlations in Topic Models

» Routine as resource for the design of learning systems

Post Info
More Details (n/a)

Added	29 Sep 2012
Updated	29 Sep 2012
Type	Journal
Year	2012
Where	ACL
Authors	Hassan Sajjad, Alexander Fraser, Helmut Schmid

Comments (0)