Digital Repository at the University of Maryland (DRUM)  >
Theses and Dissertations from UMD  >
UMD Theses and Dissertations 

Please use this identifier to cite or link to this item: http://hdl.handle.net/1903/12150

Title: Structured local exponential models for machine translation
Authors: Subotin, Michael
Advisors: Resnik, Philip
Department/Program: Linguistics
Type: Thesis
Sponsors: Digital Repository at the University of Maryland
University of Maryland (College Park, Md.)
Subjects: Computer science
Linguistics
Artificial intelligence
Keywords: Exponential models
Machine learning
Machine translation
Maximum entropy
Issue Date: 2010
Abstract: This thesis proposes a synthesis and generalization of local exponential translation models, the subclass of feature-rich translation models which associate probability distributions with individual rewrite rules used by the translation system, such as synchronous context-free rules, or with other individual aspects of translation hypotheses such as word pairs or reordering events. Unlike other authors we use these estimates to replace the traditional phrase models and lexical scores, rather than in addition to them, thereby demonstrating that the local exponential phrase models can be regarded as a generalization of standard methods not only in theoretical but also in practical terms. We further introduce a form of local translation models that combine features associated with surface forms of rules and features associated with less specific representation -- including those based on lemmas, inflections, and reordering patterns -- such that surface-form estimates are recovered as a special case of the model. Crucially, the proposed approach allows estimation of parameters for the latter type of features from training sets that include multiple source phrases, thereby overcoming an important training set fragmentation problem which hampers previously proposed local translation models. These proposals are experimentally validated. Conditioning all phrase-based probabilities in a hierarchical phrase-based system on source-side contextual information produces significant performance improvements. Extending the contextually-sensitive estimates with features modeling source-side morphology and reordering patterns yields consistent additional improvements, while further experiments show significant improvements obtained from modeling observed and unobserved inflections for a morphologically rich target language.
URI: http://hdl.handle.net/1903/12150
Appears in Collections:Linguistics Theses and Dissertations
UMD Theses and Dissertations

Files in This Item:

File Description SizeFormatNo. of Downloads
Subotin_umd_0117N_11851.pdf321.7 kBAdobe PDF244View/Open

All items in DRUM are protected by copyright, with all rights reserved.

 

DRUM is brought to you by the University of Maryland Libraries
University of Maryland, College Park, MD 20742-7011 (301)314-1328.
Please send us your comments