mt-class.org
JHU MT course
http://mt-class.org/past/jhu/2012
Georges Artrouni's mechanical brain, a translation device patented in France in 1933. (Image from Corbé by way of John Hutchins. Machine Translation : 600.468 : Spring 2012. Tuesdays and Thursdays from 3:00-4:15, Shaffer 202. Tuesdays and Thursdays from 4:15 (immediately after class) or by appointment. We wrote a TACL paper. About the outcome of our competitive homework assignments. Please cite this paper if you reuse the assignments in academic work. Senior undergraduate or first-year graduate. Some rea...
catalogue.lti.cs.cmu.edu
LTI Catalogue | Carnegie Mellon University - Language Technologies Institute
http://catalogue.lti.cs.cmu.edu/tools/116-cdec
A fast, mature decoder, alignment, and modeling toolkit for statistical machine translation and similar structure-prediction problems. Cdec is a decoder, aligner, and learning framework for statistical machine translation and similar structured prediction models developed by Chris Dyer. At the Language Technologies Institute. In Carnegie Mellon University. And lots of volunteers. Translation and alignment modeling based on. Extended tree-to-string transducers ( xRs. And do parameter tuning.
kheafield.com
kenlm . code . Kenneth Heafield
http://www.kheafield.com/code/kenlm
KenLM Language Model Toolkit. Language models. Estimation is fast and scalable due to streaming algorithms explained in the paper. Scalable Modified Kneser-Ney Language Model Estimation. Ivan Pouzyrevsky, Jonathan H. Clark, and Philipp Koehn. ACL. Sofia, Bulgaria, 4 9 August, 2013. Querying is fast and low-memory. As shown in the paper. KenLM: Faster and Smaller Language Model Queries. Edinburgh, Scotland, United Kingdom, 30 31 July, 2011. Wget -O - http:/ kheafield.com/code/kenlm.tar.gz. KENLM factor=0 ...
github.com
GitHub - redpony/cdec: Decoder, aligner, and model optimizer for statistical machine translation and other structured prediction models based on (mostly) context-free formalisms
https://github.com/redpony/cdec
Decoder, aligner, and model optimizer for statistical machine translation and other structured prediction models based on (mostly) context-free formalisms. Use Git or checkout with SVN using the web URL. Jan 17, 2016. Bug fixes when training with WER. Failed to load latest commit information. Apr 27, 2015. Use downloaded data instead of github data. Jun 17, 2015. Jan 3, 2016. Apr 27, 2015. Jul 22, 2014. Mar 3, 2015. Jun 17, 2015. Fix kenlm's use of compression libraries. Apr 9, 2015. Jan 17, 2016. C Dyer...
victor.chahuneau.fr
pycdec: A Python Interface to cdec
http://victor.chahuneau.fr/pub/pycdec
A Python Interface to. Noah A. Smith. A Python module for the. Decoder. It enables Python code to use. S fast C implementation of core finite-state and context-free inference algorithms for decoding and alignment. The high-level interface allows developers to build integrated MT applications that take advantage of the rich Python ecosystem without sacrificing computational performance. We give examples of how to interact directly with the main. Allowing direct integration of external Python libraries suc...