Using Accessor Variety Features of Source Graphemes in Machine Transliteration of English to Chinese

This work describes a grapheme-based approach of English-to-Chinese (E2C) transliteration, which includes many-to-many alignment models and conditional random fields using accessor variety (AV) as an additional feature based on source graphemes. Experimental results indicate that the AV of a given E...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiang, M. T., Chan-Hung Kuo, Wen-Lian Hsu
Format: Conference Proceeding
Language:English
Subjects:
accessor variety
Accuracy
conditional random fields
Context
direct orthographical mapping
Entropy
expectation maximization
Labeling
machine transliteration
named entity
Prediction algorithms
Training
Training data
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This work describes a grapheme-based approach of English-to-Chinese (E2C) transliteration, which includes many-to-many alignment models and conditional random fields using accessor variety (AV) as an additional feature based on source graphemes. Experimental results indicate that the AV of a given English segment can generally improve effectiveness of E2C transliteration.
ISSN:2376-6816
2376-6824
DOI:10.1109/TAAI.2011.30