Training Tree Transducers

Citations Over TimeTop 1% of 2008 papers

Abstract

Many probabilistic models for natural language are now written in terms of hierarchical tree structure. Tree-based modeling still lacks many of the standard tools taken for granted in (finite-state) string-based modeling. The theory of tree transducer automata provides a possible framework to draw on, as it has been worked out in an extensive literature. We motivate the use of tree transducers for natural language and address the training problem for probabilistic tree-to-tree and tree-to-string transducers.

Related Papers

• → A Systematic Comparison of Various Statistical Alignment Models(2003)3,917 cited
• → Hierarchical Phrase-Based Translation(2007)1,162 cited
• Stochastic inversion transduction grammars and bilingual parsing of parallel corpora(1997)
• → Scalable inference and training of context-rich syntactic translation models(2006)418 cited
• → A Smorgasbord of Features for Statistical Machine Translation(2004)260 cited