EMM NewsExplorer: http://emm.newsexplorer.eu/NewsExplorer/home/en/latest.html
More: http://emm.newsbrief.eu/overview.html
That's great. I intended to develop such a similar thing for Vietnamese. Now I got one to follow.
--
Cheers,
Vu
Thursday, 8 September 2011
Sunday, 4 September 2011
Thursday, 1 September 2011
Bilingual Sentence Aligner
Tool by Microsoft
Wednesday, 31 August 2011
Wednesday, 3 August 2011
TER-Plus (TERp)
TERp: http://www.umiacs.umd.edu/~snover/terp/
Intro
TERp is an automatic evaluation metric for Machine Translation, which takes as input a set of reference translations, and a set of machine translation output for that same data. It aligns the MT output to the reference translations, and measures the number of 'edits' needed to transform the MT output into the reference translation. TERp is an extension of TER (Translation Edit Rate) that utilizes phrasal substitutions (using automatically generated paraphrases), stemming, synonyms, relaxed shifting constraints and other improvements.
Intro
TERp is an automatic evaluation metric for Machine Translation, which takes as input a set of reference translations, and a set of machine translation output for that same data. It aligns the MT output to the reference translations, and measures the number of 'edits' needed to transform the MT output into the reference translation. TERp is an extension of TER (Translation Edit Rate) that utilizes phrasal substitutions (using automatically generated paraphrases), stemming, synonyms, relaxed shifting constraints and other improvements.
Labels:
EBMT,
evaluation,
links,
machine translation,
research,
SMT,
statistical machine translation,
toolkits
Open Source Machine Translation System Combination
Intro
MANY is an MT system combination software which architecture is described is the following picture :
The combination can be decomposed into three steps
--
Cheers,
Vu
MANY is an MT system combination software which architecture is described is the following picture :
The combination can be decomposed into three steps
- 1-best hypotheses from all M systems are aligned in order to build M confusion networks (one for each system considered as backbone).
- All CNs are connected into a single lattice. The first nodes of each CN are connected to a unique first node with probabilities equal to the priors probabilities assigned to the corresponding backbone. The final nodes are connected to a single final node with arc probability of one.
- A token pass decoder is used along with a language model to decode the resulting lattice and the best hypothesis is generated.
--
Cheers,
Vu
Subscribe to:
Posts (Atom)