Exploiting a Probabilistic Hierarchical Model for Generation

Previous stochastic approaches to generation do not include a tree-based representation of syntax. While this may be adequate or even advantageous for some applications, other applications profit from using as much syntactic knowledge as is available, leaving to a stochastic model only those issues that are not determined by the grammar. We present initial resuits showing that a tree-based model derived from a tree-annotated corpus improves on a tree model derived from an unannotated corpus, and that a tree-based stochastic model with a handcrafted grammar outpertbrms both.

• Type: Conference
• Year: 2000
• Where: COLING
• Authors: Srinivas Bangalore, Owen Rambow
• Keywords: COLING 2000, COLING 2008, Stochastic Model, Tree-based Model, Tree-based Stochastic Model