Syntax-Driven Machine Translation as a Model of ESL Revision

In this work, we model the writing revision process of English as a Second Language (ESL) students with syntax-driven machine translation methods. We compare two approaches: tree-to-string transformations (Yamada and Knight, 2001) and tree-to-tree transformations (Smith and Eisner, 2006). Results suggest that while the tree-to-tree model provides a greater coverage, the tree-to-string approach offers a more plausible model of ESL learners' revision writing process.