PUBLIC MARKS with tags taln & google

An interesting presentiation at Google Tech Talks about different interfaces to query semantic data. Casual users were presented with 4 increasingly formal systems: keyword search, natural language search, controlled language search, and a graphical interface to build query patterns. Interestingly enough, the users liked natural language best, although keyword queries gave more accurate results.

Mouais. Seulement en anglais alors?

Here at Google Research we have been using word n-gram models for a variety of R&D projects, such as statistical machine translation, speech recognition, spelling correction, entity detection, information extraction, and others. While such models have usually been estimated from training corpora containing at most a few billion words, we have been harnessing the vast power of Google's datacenters and distributed processing infrastructure to process larger and larger training corpora. We found that there's no data like more data, and scaled up the size of our data by one order of magnitude, and then another, and then one more - resulting in a training corpus of one trillion words from public Web pages.