Sciweavers

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

14

CICLING
2009
Springer

favoriteEmaildiscussreport

151views Natural Language Processing» more CICLING 2009»

Exploiting Parallel Treebanks to Improve Phrase-Based Statistical Machine Translation

14 years 4 months ago

Exploiting Parallel Treebanks to Improve Phrase-Based Statistical Machine Translation

Download tlt07.uib.no

We use existing tools to automatically build two parallel treebanks from existing parallel corpora. We then show that combining the data extracted from both the treebanks and the corpora into a single translation model can improve the translation quality in a baseline phrasebased statistical machine translation system.

John Tinsley, Mary Hearne, Andy Way

Real-time Traffic

CICLING 2009 | Natural Language Processing | Parallel Corpora | Parallel Treebanks |

claim paper

Related Content

» Accurate NonHierarchical PhraseBased Translation

» An Efficient ShiftReduce Decoding Algorithm for PhrasedBased Machine Translation

» Soft Syntactic Constraints for Hierarchical PhrasedBased Translation

» Syntactically Lexicalized PhraseBased SMT

» Improved Statistical Machine Translation for ResourcePoor Languages Using Related Resource...

» Segmentation and alignment of parallel text for statistical machine translation

» Urdu and Hindi Translation and sharing of linguistic resources

» Improved Sentence Alignment on Parallel Web Pages Using a Stochastic Tree Alignment Model

» Language and Translation Model Adaptation using Comparable Corpora

Post Info
More Details (n/a)

Added	24 Nov 2009
Updated	24 Nov 2009
Type	Conference
Year	2009
Where	CICLING
Authors	John Tinsley, Mary Hearne, Andy Way

Comments (0)