Loïc Barrault.

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.

where λi is the weight of the feature function hi.

Feature functions used:

- The LM probability
- The system prior, corresponding to the probability of choosing a system as backbone.
- The words scores: currently, each word has a score equal to the prior of the system which proposed it
- The word-length penalty of the word sequence,
- The null-penalty corresponding to the number of null-arcs (or epsilon arcs) crossed to obtain the hypothesis.

Version |
Date |
Descripton | Download |

v1 (current version) |
12/07/09 | First version with Confusion Network generation and Token Pass decoder. | [MANY SVN] (google code) |

TERp website : http://www.umiacs.umd.edu/~snover/terp/

SPHINX4 website : http://cmusphinx.sourceforge.net/sphinx4/

SRILM website : http://www.speech.sri.com/projects/srilm/