We describe Experiment.perl, an experimental management system, that allows the execution of the entire training and testing pipeline of a machine translation experiment with one configuration files. When carrying out multiple experimental runs with changed settings, Experiment.perl automatically detects which steps need to be re-run and which can be re-used.
Extending Hiero Decoding in Moses with Cube Growing
Hierarchical phrase-based (Hiero) models have richer expressiveness than phrase-based models and have shown promising translation quality gains for many language pairs whose syntactic divergences, such as reordering, could be better captured. However, their expressiveness comes at a high computational cost in decoding, which is induced by huge dynamic programs associated with language model integrated decoding, where the search space is lexically exploded and exact search often becomes intractable. Cube pruning and growing are two approximate search algorithms to make decoding much more efficient. In this article, we describe an extension to the Hiero decoder of the Moses toolkit by providing cube growing as an alternative to cube pruning, with an additional parameter similar to Jane's cube growing implementation that is not present in the original one. We also report experimental results on a full-scale NIST MT08 Chinese-English translation task.
We describe an open-source implementation of the Margin Infused Relaxed Algorithm (MIRA) for statistical machine translation (SMT). The implementation is part of the Moses toolkit and can be used as an alternative to standard minimum error rate training (MERT). A description of the implementation and its usage on core feature sets as well as large, sparse feature sets is given and we report experimental results comparing the performance of MIRA with MERT in terms of translation quality and stability.
Vicent Alabau, Ragnar Bonk, Christian Buck, Michael Carl, Francisco Casacuberta, Mercedes García-Martínez, Jesús González, Philipp Koehn, Luis Leiva, Bartolomé Mesa-Lao, Daniel Ortiz, Herve Saint-Amand, Germán Sanchis and Chara Tsoukala
We describe an open source workbench that offers advanced computer aided translation (CAT) functionality: post-editing machine translation (MT), interactive translation prediction (ITP), visualization of word alignment, extensive logging with replay mode, integration with eye trackers and e-pen.