Casey Whitelaw’s research while affiliated with Google Inc. and other places

We have designed, implemented and evaluated an end-to-end system spellchecking and autocorrection system that does not require any manually annotated training data. The World Wide Web is used as a large noisy corpus from which we infer knowledge about misspellings and word usage. This is used to build an error model and an n-gram language model. A small secondary set of news texts with artificially inserted misspellings are used to tune confidence classifiers. Because no manual annotation is required, our system can easily be instantiated for new languages. When evaluated on human typed data with real misspellings in English and German, our web-based systems outperform baselines which use candidate corrections based on hand-curated dictionaries. Our system achieves 3.8% total error rate in English. We show similar improvements in preliminary results on artificial data for Russian and Arabic.

Automatic recognition of named entities such as people, places, organizations, books, and movies across the entire web presents a number of challenges, both of scale and scope. Data for training general named entity recognizers is difficult to come by, and efficient machine learning methods are required once we have found hundreds of millions of labeled observations. We present an implemented system that addresses these issues, including a method for automatically generating training data, and a multi-class online classification training method that learns to recognize not only high level categories such as place and person, but also more fine-grained categories such as soccer players, birds, and universities. The resulting system gives precision and recall performance comparable to that obtained for more limited entity types in much more structured domains such as company recognition in newswire, even though web documents often lack consistent capitalization and grammatical sentence construction.