TY  - GEN
AB  - Pipeline systems, widely used in natural language processing and other fields, process data through sequential stages to improve efficiency, manage search complexity, and reuse components. Despite their prevalence, little systematic work has examined how these systems function or how best to improve them. This dissertation defines a formal framework based on shared properties of pipelines across domains such as parsing, speech recognition, machine translation, and image classification. It introduces quantitative metrics describing constraint characteristics and demonstrates that commonly used measures of constraint quality are poor predictors of performance. The findings show that systematically modifying constraint properties can meaningfully affect pipeline performance, offering broadly applicable guidance for analyzing and improving pipeline systems.
AD  - Oregon Health and Science University
AU  - Hollingshead, Kristy
DA  - 2010
DO  - 10.6083/M49K4860
DO  - DOI
ED  - Roark, Brian
ED  - Advisor
ID  - 368
KW  - Algorithms
KW  - Natural Language Processing
KW  - Linguistics
KW  - Methods
KW  - Computers
KW  - automatic speech recognition
KW  - pipeline
KW  - pattern recognition
KW  - computer science
L1  - https://digitalcollections.ohsu.edu/record/368/files/369_etd.pdf
L2  - https://digitalcollections.ohsu.edu/record/368/files/369_etd.pdf
L4  - https://digitalcollections.ohsu.edu/record/368/files/369_etd.pdf
LK  - https://digitalcollections.ohsu.edu/record/368/files/369_etd.pdf
N2  - Pipeline systems, widely used in natural language processing and other fields, process data through sequential stages to improve efficiency, manage search complexity, and reuse components. Despite their prevalence, little systematic work has examined how these systems function or how best to improve them. This dissertation defines a formal framework based on shared properties of pipelines across domains such as parsing, speech recognition, machine translation, and image classification. It introduces quantitative metrics describing constraint characteristics and demonstrates that commonly used measures of constraint quality are poor predictors of performance. The findings show that systematically modifying constraint properties can meaningfully affect pipeline performance, offering broadly applicable guidance for analyzing and improving pipeline systems.
PB  - Oregon Health and Science University
PY  - 2010
T1  - Formalizing the use and characteristics of constraints in pipeline systems
TI  - Formalizing the use and characteristics of constraints in pipeline systems
UR  - https://digitalcollections.ohsu.edu/record/368/files/369_etd.pdf
Y1  - 2010
ER  -