Word folding: taking the snapshot of words instead of the whole

Authors:
Jin-Dong Kim;Jun’ichi Tsujii
Affiliations:
University of Tokyo, Tokyo, Japan;University of Tokyo, Tokyo, Japan
Venue:
IJCNLP'04 Proceedings of the First international joint conference on Natural Language Processing
Year:
2004

Citing 7
Cited 2

C4.5: programs for machine learning

C4.5: programs for machine learning
Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging

Computational Linguistics
A maximum entropy approach to natural language processing

Computational Linguistics
Building a large annotated corpus of English: the penn treebank

Computational Linguistics - Special issue on using large corpora: II
Representing text chunks

EACL '99 Proceedings of the ninth conference on European chapter of the Association for Computational Linguistics
Self-organizing Markov models and their application to part-of-speech tagging

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Equations for part-of-speech tagging

AAAI'93 Proceedings of the eleventh national conference on Artificial intelligence

ME-based biomedical named entity recognition using lexical knowledge

ACM Transactions on Asian Language Information Processing (TALIP)
Semantic Classification of Bio-Entities Incorporating Predicate-Argument Features

IEICE - Transactions on Information and Systems

Quantified Score

Hi-index	0.02

Visualization

Abstract

The snapshot of a word means the most informative fragment of the word. By taking the snapshot instead of the whole, the value space of lexical features can be significantly reduced. From the perspective of machine learning, a small space of feature values implies a loss of information but less data-spareness and less unseen data. The snapshot of words can be taken by using the word folding technique, the goal of which is to reduce the value space of lexical features while minimizing the loss of information.