Paper: Automatic Analysis of Rhythmic Poetry with Applications to Generation and Translation

ACL ID D10-1051
Title Automatic Analysis of Rhythmic Poetry with Applications to Generation and Translation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2010
Authors

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. We then use these word-stress patterns, in ad- dition to rhyme and discourse models, to gen- erate English love poetry. Finally, we trans- late Italian poetry into English, choosing tar- get realizations that conform to desired rhyth- mic patterns.