Workshop on Semi-supervised Learning for Natural Language Processing at NAACL HLT 2009

Interesting write-up of the problems in semi-supervised learning for NLP.
Parts that interest me:
1. "What are the different classes of NLP problem structures (e.g. sequences, trees, N-best lists) and what algorithms are best suited for each class? For instance, can graph-based algorithms be successfully applied to sequence-to-sequence problems like machine translation, or are self-training and feature-based methods the only reasonable choices for these problems? "
2. What kinds of NLP-specific background knowledge can we exploit to aid semi-supervised learning? Recent learning paradigms such as constraint-driven learning and prototype learning take advantage of our domain knowledge about particular NLP tasks?
3. Many semi-supervised learning methods (e.g. transductive SVM, graph-based methods) have been originally developed for binary classification problems. NLP problems often pose new challenges to these techniques, involving more complex structure that can violate many of the underlying assumptions.