Sciweavers

Share
ACL
2010

Improved Unsupervised POS Induction through Prototype Discovery

10 years 11 months ago
Improved Unsupervised POS Induction through Prototype Discovery
We present a novel fully unsupervised algorithm for POS induction from plain text, motivated by the cognitive notion of prototypes. The algorithm first identifies landmark clusters of words, serving as the cores of the induced POS categories. The rest of the words are subsequently mapped to these clusters. We utilize morphological and distributional representations computed in a fully unsupervised manner. We evaluate our algorithm on English and German, achieving the best reported results for this task.
Omri Abend, Roi Reichart, Ari Rappoport
Added 10 Feb 2011
Updated 10 Feb 2011
Type Journal
Year 2010
Where ACL
Authors Omri Abend, Roi Reichart, Ari Rappoport
Comments (0)
books