A unified local and global model for discourse coherence.
Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, 436-443. Association for Computational Linguistics, New York City, NY, USA. 2007
要旨
We present a model for discourse coherence which combines the local entitybased approach of (Barzilay and Lapata, 2005) and the HMM-based content model of (Barzilay and Lee, 2004). Unlike the mixture model of (Soricut and Marcu, 2006), we learn local and global features jointly, providing a better theoretical explanation of how they are useful. As the local component of our model we adapt (Barzilay and Lapata, 2005) by relaxing independence assumptions so that it is effective when estimated generatively. Our model performs the ordering task competitively with (Soricut and Marcu, 2006), and significantly better than either of the models it is based on.