Word Midas Powered by StringNet: Discovering Lexicogrammatical Constructions in Situ

AbstractAdult second language learners face the daunting but underappreciated task of mastering patterns of language use that are neither products of fully productive grammar rules nor frozen items to be memorized. Word Midas, a web browser extention, targets this uncharted territory of lexicogrammar by detecting multiword tokens of lexicogrammatical patterning in real time in situ within the noisy digital texts from the user’s unscripted web browsing or other digital venues. The language model powering Word Midas is StringNet, a densely cross-indexed navigable network of one billion lexicogrammatical patterns of English. These resources are described and their functionality is illustrated with a detailed scenario.