Sciweavers

16 search results - page 2 / 4
» Unsupervised Learning of Morphology without Morphemes
Sort
View
CLEF
2008
Springer
13 years 7 months ago
Allomorfessor: Towards Unsupervised Morpheme Analysis
Many modern natural language processing applications would benefit from automatic morphological analysis of words, especially when dealing with morphologically rich languages. Con...
Oskar Kohonen, Sami Virpioja, Mikaela Klami
CORR
2002
Springer
82views Education» more  CORR 2002»
13 years 5 months ago
Using eigenvectors of the bigram graph to infer morpheme identity
This paper describes the results of some experiments exploring statistical methods to infer syntactic categories from a raw corpus in an unsupervised fashion. It shares certain po...
Mikhail Belkin, John A. Goldsmith
COLING
2010
13 years 13 days ago
EMMA: A novel Evaluation Metric for Morphological Analysis
We present a novel Evaluation Metric for Morphological Analysis (EMMA) that is both linguistically appealing and empirically sound. EMMA uses a graphbased assignment algorithm, op...
Sebastian Spiegler, Christian Monson
CLEF
2008
Springer
13 years 7 months ago
ParaMor and Morpho Challenge 2008
ParaMor, our unsupervised morphology induction system performed well at Morpho Challenge 2008. When ParaMor's morphological analyses, which specialize at identifying inflecti...
Christian Monson, Jaime G. Carbonell, Alon Lavie, ...
CLEF
2009
Springer
13 years 3 months ago
Unsupervised Morphological Analysis by Formal Analogy
Abstract. While classical approaches to unsupervised morphology acquisition often rely on metrics based on information theory for identifying morphemes, we describe a novel approac...
Jean-François Lavallée, Philippe Lan...