Paper: Syntax-Driven Machine Translation as a Model of ESL Revision

ACL ID C10-2157
Title Syntax-Driven Machine Translation as a Model of ESL Revision
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

In this work, we model the writing re- vision 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 trans- formations (Smith and Eisner, 2006). Results suggest that while the tree-to- tree model provides a greater cover- age, the tree-to-string approach offers a more plausible model of ESL learn- ers’ revision writing process.