TMODS:ENG-CZE -- query translation

 
LINDAT / CLARIAH-CZ
  Authors
Tamchyna, Aleš and Bojar, Ondřej
  Item identifier
http://hdl.handle.net/11234/1-1581
 Project URL
http://ufal.mff.cuni.cz/grants/amalach
 Date issued
2015
 Type
toolService
 Language(s)
Czech , English
 Description
AMALACH project component TMODS:ENG-CZE; machine translation of queries from Czech to English. This archive contains models for the Moses decoder (binarized, pruned to allow for real-time translation) and configuration files for the MTMonkey toolkit. The aim of this package is to provide a full service for Czech->English translation which can be easily utilized as a component in a larger software solution. (The required tools are freely available and an installation guide is included in the package.) The translation models were trained on CzEng 1.0 corpus and Europarl. Monolingual data for LM estimation additionally contains WMT news crawls until 2013.
 Publisher
Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
 Acknowledgement

Ministerstvo kultury České republiky

Project code: DF12P01OVV022

Project name: Zpřístupnění rozsáhlého video archivu kulturního dědictví pomocí metod automatického rozpoznávání mluvené řeči a strojového překladu. (AMALACH)

 Subject(s)
machine translation query translationn
 Collection(s)
LINDAT / CLARIAH-CZ Data & Tools
Show full item record
 

 Files in this item

This item is
Publicly Available
and licensed under:
Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
Distributed under Creative Commons Attribution Required Noncommercial Share Alike
Icon
Name
TMODS-ENG-CZE-query.tar.gz
Size
2.74 GB
Format
application/x-gzip
Description
Model files for TMODS:ENG-CZE query translation
MD5
41246e0b67c36c6b872c8d4bc9281e36
 Download file  Preview
 File Preview  
  • TMODS-ENG-CZE-query
    • README.txt1 kB
    • model
      • biglm.trie1 GB
      • worker.cfg175 B
      • moses.ini844 B
      • appserver.cfg120 B
      • ttable.lemmas.minphr933 MB
      • smalllm.trie250 MB
      • ttable.minphr975 MB
Icon
Name
README.txt
Size
1.28 KB
Format
Text file
MD5
92d655ca32f3f8ec76d77d3c3d3f27b0
 Download file  Preview
 File Preview   
TMODS:ENG-CZE -- query translation component
============================================

Installation:

1) Download and compile the Moses decoder:

  (Requires Boost, libXML and CMPH.)

  git clone https://github.com/moses-smt/mosesdecoder.git
  cd mosesdecoder
  ./bjam --with-xmlrpc=<path-to-libxml> --max-kenlm-order=12 --with-cmph=<path-to-cmph-library>
  cd ..

2) Download and configure MTMonkey:
  
  (See MTMonkey documentation for installation requirements.)

  git clone https://github.com/ufal/mtmonkey
  cd mtmonkey
  git checkout chimera_preprocessing
  # the tested commit ID is d0e3175ee112a3fdd4790ccd1b0ff4e5d90c8d04
  cd ..

3) Install MorphoDita and its Python bindings.

  Follow the steps described here:

  http://ufal.mff.cuni.cz/morphodita/install#python_installation

4) Download Morphodita model for Czech:

  http://hdl.handle.net/11858/00-097C-0000-0023-68D8-1

  Copy the model in the MTMonkey directory:

  cp czech-morfflex-pdt-131112.tagger-fast mtmonkey

5) Start t . . .