TY  - GEN
AB  - Confrontation naming tasks such as the Philadelphia Naming Test (PNT) are essential tools for the assessment and treatment of people with aphasia. One challenge to clinical use of the PNT is the complexity of its scoring guidelines. We build on work towards automatic classification of paraphasias by (1) demonstrating that machine learning models substantially improve performance on the paraphasia classification task, (2) providing insight into the behavior of the highest-performing model, and (3) reporting results on experiments with contextual semantic and item-level information. Our best model improves 8.1 F1 points over a manually-constructed decision tree classifier. For development of the semantic features, we used crowdsourcing methods to construct a dataset of linguistic contexts from the visually presented items on the PNT assessment.
AD  - Oregon Health and Science University
AD  - Oregon Health and Science University
AD  - Oregon Health and Science University
AD  - Oregon Health and Science University
AU  - McKinney-Bock, Katy
AU  - Li, Linying
AU  - Fergadiotis, Gerasimos
AU  - Bedrick, Steven
DA  - 2020
DO  - 10.6083/5d86p0976
DO  - DOI
ID  - 8371
KW  - Natural Language Processing
KW  - Machine Learning
KW  - Aphasia
KW  - philadelphia naming test
KW  - paraphasia
KW  - aphasiology
KW  - language assessment
L1  - https://digitalcollections.ohsu.edu/record/8371/files/ResearchWeek.2020.McKinneyKaty.pdf
L2  - https://digitalcollections.ohsu.edu/record/8371/files/ResearchWeek.2020.McKinneyKaty.pdf
L4  - https://digitalcollections.ohsu.edu/record/8371/files/ResearchWeek.2020.McKinneyKaty.pdf
LK  - https://digitalcollections.ohsu.edu/record/8371/files/ResearchWeek.2020.McKinneyKaty.pdf
N2  - Confrontation naming tasks such as the Philadelphia Naming Test (PNT) are essential tools for the assessment and treatment of people with aphasia. One challenge to clinical use of the PNT is the complexity of its scoring guidelines. We build on work towards automatic classification of paraphasias by (1) demonstrating that machine learning models substantially improve performance on the paraphasia classification task, (2) providing insight into the behavior of the highest-performing model, and (3) reporting results on experiments with contextual semantic and item-level information. Our best model improves 8.1 F1 points over a manually-constructed decision tree classifier. For development of the semantic features, we used crowdsourcing methods to construct a dataset of linguistic contexts from the visually presented items on the PNT assessment.
PB  - Oregon Health and Science University
PY  - 2020
T1  - Improving machine learning models of paraphasia classification using crowdsourced semantic features
TI  - Improving machine learning models of paraphasia classification using crowdsourced semantic features
UR  - https://digitalcollections.ohsu.edu/record/8371/files/ResearchWeek.2020.McKinneyKaty.pdf
Y1  - 2020
ER  -