Mot en trebank for amerikanorsk

Authors

  • Andre Kåsen Nasjonalbiblioteket

DOI:

https://doi.org/10.5617/osla.8501

Abstract

This article presents a method for automatic assignment of syntactic dependency relations to the corpus of American Norwegian speech (CANS). Different machine learning techniques and corpora are used. Finally, an accuracy measure is computed and compared with a relatively new treebank for spoken Norwegian.

Downloads

Published

2021-01-22 — Updated on 2022-01-03

Versions

opyright (c) 2014-2020 Simon Fraser University * Copyright (c) 2003-2020 John Willinsky * Distributed under the GNU GPL v3. For full terms see the file docs/COPYING. * * @brief Common site frontend footer. * * @uses $isFullWidth bool Should this page be displayed without sidebars? This * represents a page-level override, and doesn't indicate whether or not * sidebars have been configured for thesite. *}