You've probably heard by now that bees are dying in record numbers. They're being poisoned by pesticides while urbanization encroaches on bees' natural habitats, leaving them with fewer places to live and fewer wildflowers to feed on, says Harvard biologist James Crall, who studies bumblebees. The die-off comes as the world's human population is expected to grow from 7 billion in 2010 to 9.8 billion in 2050; as incomes rise, food producers will need to supply 56 percent more calories to meet growing demand, according to a December report by the World Resource Institute. That's going to be hard to do without the wild bees farmers have traditionally relied on to pollinate their crops. "An enormous amount of our food crops depend on animal pollinators," Crall says, highlighting fruits, nuts, and berries.

Part-of-speech (POS) tagging is a fundamental component for performing natural language tasks such as parsing, information extraction, and question answering. When POS taggers are trained in one domain and applied in significantly different domains, their performance can degrade dramatically. We present a methodology for rapid adaptation of POS taggers to new domains. Our technique is unsupervised in that a manually annotated corpus for the new domain is not necessary. We use suffix information gathered from large amounts of raw text as well as orthographic information to increase the lexical coverage. We present an experiment in the Biological domain where our POS tagger achieves results comparable to POS taggers specifically trained to this domain. Many machine-learning and statistical techniques employed for POS tagging train a model on an annotated corpus, such as the Penn Treebank (Marcus et al, 1993). Most state-of-the-art POS taggers use two main sources of information: 1) Information about neighboring tags, and 2) Information about the word itself. Methods using both sources of information for tagging are: Hidden Markov Modeling, Maximum Entropy modeling, and Transformation Based Learning (Brill, 1995).