Microsoft Technology Licensing, LLC

Microsoft Corporaiton

Colin A Cherry

Christopher Brian Quirk

Arul A Menezes

Kristina Nikolova Toutanova

Hoifung Poon

Described is a technology for performing unsupervised learning using global features extracted from unlabeled examples. The unsupervised learning process may be used to train a log-linear model, such as for use in morphological segmentation of words. For example, segmentations of the examples are sampled based upon the global features to produce a segmented corpus and log-linear model, which are then iteratively reprocessed to produce a final segmented corpus and a log-linear model.

Unsupervised learning using global features, including for log-linear model word segmentation

In one embodiment of the present invention, a decoder receives a dependency tree as a source language input and accesses a set of statistical models that produce outputs combined in a log linear framework. The decoder also accesses a table of treelet translation pairs and returns a target dependency tree based on the source dependency tree, based on access to the table of treelet translation pairs, and based on the application of the statistical models.

Extracting treelet translation pairs

Machine translation system incorporating syntactic dependency treelets into a statistical framework

Order model for dependency structure

Projecting dependencies to generate target language dependency structure

Growing community of inventors

Edmonton, Canada

Colin A Cherry