Named entity transcription with pairn-gram models
Martin Jansche, Richard Sproat · 2009
We submitted results for each of the eight shared tasks. Except for Japanese name kanji restoration, which uses a noisy channel model, our Standard Run submissions were produced by generative long-range pair n-gram models, which we mostly augmented with publicly available data (either from LDC datasets or mined from Wikipedia) for the Non-Standard Runs.