TY  - JOUR
A1  - Arslan, Seçkin
A1  - Gür, Eren
A1  - Felser, Claudia
T1  - Predicting the sources of impaired wh-question comprehension in non-fluent aphasia
BT  - a cross-linguistic machine learning study on Turkish and German
JF  - Cognitive neuropsychology
N2  - This study investigates the comprehension of wh-questions in individuals with aphasia (IWA) speaking Turkish, a non-wh-movement language, and German, a wh-movement language. We examined six German-speaking and 11 Turkish-speaking IWA using picture-pointing tasks. Findings from our experiments show that the Turkish IWA responded more accurately to both object who and object which questions than to subject questions, while the German IWA performed better for subject which questions than in all other conditions. Using random forest models, a machine learning technique used in tree-structured classification, on the individual data revealed that both the Turkish and German IWA’s response accuracy is largely predicted by the presence of overt and unambiguous case marking. We discuss our results with regard to different theoretical approaches to the comprehension of wh-questions in aphasia.
KW  - Non-fluent aphasia
KW  - random forest algorithm
KW  - sentence comprehension
KW  - wh-in-situ
KW  - wh-questions
KW  - wh-movement
Y1  - 2017
U6  - https://doi.org/10.1080/02643294.2017.1394284
SN  - 0264-3294
SN  - 1464-0627
VL  - 34
SP  - 312
EP  - 331
PB  - Taylor & Francis
CY  - Abingdon
ER  - 
TY  - GEN
A1  - Arslan, Seçkin
A1  - Gür, Eren
A1  - Felser, Claudia
T1  - Predicting the sources of impaired wh-question comprehension in non-fluent aphasia
BT  - a cross-linguistic machine learning study on Turkish and German
T2  - Postprints der Universität Potsdam : Humanwissenschaftliche Reihe
N2  - This study investigates the comprehension of wh-questions in individuals with aphasia (IWA) speaking Turkish, a non-wh-movement language, and German, a wh-movement language. We examined six German-speaking and 11 Turkish-speaking IWA using picture-pointing tasks. Findings from our experiments show that the Turkish IWA responded more accurately to both object who and object which questions than to subject questions, while the German IWA performed better for subject which questions than in all other conditions. Using random forest models, a machine learning technique used in tree-structured classification, on the individual data revealed that both the Turkish and German IWA’s response accuracy is largely predicted by the presence of overt and unambiguous case marking. We discuss our results with regard to different theoretical approaches to the comprehension of wh-questions in aphasia.
T3  - Zweitveröffentlichungen der Universität Potsdam : Humanwissenschaftliche Reihe - 464 
KW  - Non-fluent aphasia
KW  - random forest algorithm
KW  - sentence comprehension
KW  - wh-in-situ
KW  - wh-questions
KW  - wh-movement
Y1  - 2018
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:517-opus4-412717
IS  - 464
ER  -