000009252 001__ 9252
000009252 005__ 20240408090625.0
000009252 0247_ $$2DOI$$a10.6083/rx913q54v
000009252 037__ $$aIR
000009252 041__ $$aeng
000009252 245__ $$aFine-tuning BERT for the semantic classifier of the PNT
000009252 260__ $$bOregon Health and Science University
000009252 269__ $$a2021
000009252 336__ $$aAbstract
000009252 520__ $$aAphasia is a language disorder resulting from a stroke or brain injury. Individuals with aphasia make paraphasias: speech errors consisting of an unintended word. This work focuses on automatically classifying semantic similarity of the paraphasia. We train a modern language model called BERT alongside a binary classifier to categorize each transcribed response to a PNT item as semantically similar to the target or not. We evaluate the accuracy of this classification compared with clinician scores. We also compare the results of this model to a previously used language model called word2vec.
000009252 540__ $$fCC BY
000009252 542__ $$fIn copyright - joint owners
000009252 650__ $$aSpeech$$026226
000009252 650__ $$aMachine Learning$$011449
000009252 650__ $$aAphasia$$014975
000009252 650__ $$aNatural Language Processing$$022716
000009252 650__ $$aStroke$$032460
000009252 650__ $$aBrain Injuries, Traumatic$$011616
000009252 6531_ $$alanguage model
000009252 691__ $$aSchool of Medicine$$041369
000009252 692__ $$aDepartment of Computer Science and Electrical Engineering$$041404
000009252 7001_ $$aSalem, Alexandra C.$$uOregon Health and Science University$$041354
000009252 7001_ $$aBedrick, Steven$$uOregon Health and Science University$$041354
000009252 7001_ $$aGale, Robert$$uOregon Health and Science University$$041354
000009252 711__ $$aResearch Week$$uOregon Health and Science University$$d2021
000009252 8564_ $$9787eaefd-6e8c-4a0f-bbfb-145eb14ccf89$$s44920$$uhttps://digitalcollections.ohsu.edu/record/9252/files/Salem-Alexandra-OHSU-ResearchWeek-2021.pdf
000009252 905__ $$a/rest/prod/rx/91/3q/54/rx913q54v
000009252 980__ $$aResearch Week