Year: 2009
Type: conference-paper
Abstract: 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.
Source: Named Entities Workshop (NEWS)
Authors: Martin Jansche, Richard Sproat
Institutions: Google (United States), Oregon Health & Science University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W2039724694