Next:
Abstract
Assigning Phrase Breaks from
Part-of-Speech Sequences
Paul Taylor
and
Alan W Black
Centre for Speech Technology Research,
University of Edinburgh,
80 South Bridge Edinburgh EH1 1HN
email:
[email protected]
[email protected]
Computer Speech and Language
, 12, pp 99-117, 1998.
Abstract
Introduction
Overview of the Algorithm
POS Sequence Model
The Phrase Break Model
Combining the Models
Data and Evaluation
Performance Criteria
Testing Methodology
Part-of-Speech Tagging
Part-of-Speech Sequence Models
Punctuation, Content Words and Function Words
Larger POS Tagsets
Smoothing POS Sequence Models
Varying POS sequence length
Minor and Major
Using Distance Information: the Phrase Break Model
Varying the Order of the N-gram
Discussion
Interpreting results
Comparison with other systems
Future Improvements
Bibliography
Acknowledgements
Appendix: Tagsets
About this document ...
Alan W Black
1999-03-20