We employ statistical methods to analyze, generate, and translate rhythmic poetry. We first apply unsupervised learning to reveal word-stress patterns in a corpus of raw poetry. W...
Generating expository dialogue from monologue is a task that poses an interesting and rewarding challenge for Natural Language Processing. This short paper has three aims: firstly...
We present a discourse-level Tree Adjoining Grammar which tightly integrates syntax and discourse levels, including a representation for discourse entities. We show that this tech...
In this paper, we introduce a layout description and generation model, GBLD, based on the notions and elements of L-systems and context-free grammars. Our layout model is compatib...
This paper discusses two problems that arise in the Generation of Referring Expressions: (a) numeric-valued attributes, such as size or location; (b) perspective-taking in referen...