Part of speech tagging for Amharic using conditional random fields

Authors:
Sisay Fissaha Adafre
Affiliations:
University of Amsterdam, Amsterdam, The Netherlands
Venue:
Semitic '05 Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages
Year:
2005

Citing 4
Cited 3

Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Shallow parsing with conditional random fields

NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons

CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
Automatic tagging of Arabic text: from raw text to base phrase chunks

HLT-NAACL-Short '04 Proceedings of HLT-NAACL 2004: Short Papers

Methods for Amharic part-of-speech tagging

AfLaT '09 Proceedings of the First Workshop on Language Technologies for African Languages
An Amharic stemmer: reducing words to their citation forms

Semitic '07 Proceedings of the 2007 Workshop on Computational Approaches to Semitic Languages: Common Issues and Resources
Introduction to the special issue on African Language Technology

Language Resources and Evaluation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We applied Conditional Random Fields (CRFs) to the tasks of Amharic word segmentation and POS tagging using a small annotated corpus of 1000 words. Given the size of the data and the large number of unknown words in the test corpus (80%), an accuracy of 84% for Amharic word segmentation and 74% for POS tagging is encouraging, indicating the applicability of CRFs for a morphologically complex language like Amharic.