FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378717275> ?p ?o ?g. }

• W4378717275 abstract "Natural language processing (NLP) holds promise to transform psychiatric research and practice. A pertinent example is the success of NLP in automatic detection of speech disorganization in formal thought disorder (FTD). However, we lack an understanding of what precisely common NLP metrics measure and how they relate to theoretical accounts of FTD. We propose tackling these questions by using deep generative language models to simulate FTD-like narratives by perturbing computational parameters instantiating theory-based mechanisms of FTD. We simulated FTD-like narratives using GPT-2 by either increasing word selection stochasticity or limiting the model’s memory span. We then examined the sensitivity of common NLP measures of derailment (semantic distance between consecutive words or sentences) and ‘tangentiality’ (how quickly meaning drifts away from the topic) in detecting, and dissociating, the two underlying impairments. Both parameters led to narratives characterized by greater semantic distance between consecutive sentences. Conversely, semantic distance between words was increased by increasing stochasticity, but decreased by limiting memory span. An NLP measure of tangentiality was uniquely predicted by limited memory span. The effects of limited memory span were non-monotonic, in that ‘forgetting’ the global context resulted in sentences that were semantically closer to their local, intermediate, context. Finally, different methods for encoding the meaning of sentences varied dramatically in performance. This work validates a simulation-based approach as a valuable tool for hypothesis generation and mechanistic analysis of NLP markers in psychiatry. To facilitate dissemination of this approach, we accompany the paper with a hands-on Python tutorial." @default.
• W4378717275 created "2023-05-30" @default.
• W4378717275 creator A5044364722 @default.
• W4378717275 creator A5069337982 @default.
• W4378717275 creator A5073964938 @default.
• W4378717275 date "2023-05-01" @default.
• W4378717275 modified "2023-10-09" @default.
• W4378717275 title "Theory Driven Analysis of Natural Language Processing Measures of Thought Disorder using Generative Language Modeling." @default.
• W4378717275 cites W1267646904 @default.
• W4378717275 cites W1439999129 @default.
• W4378717275 cites W1606311999 @default.
• W4378717275 cites W1873829037 @default.
• W4378717275 cites W1966163124 @default.
• W4378717275 cites W1967991178 @default.
• W4378717275 cites W1970472806 @default.
• W4378717275 cites W1973196171 @default.
• W4378717275 cites W1981745005 @default.
• W4378717275 cites W1988604782 @default.
• W4378717275 cites W1989291882 @default.
• W4378717275 cites W1989588419 @default.
• W4378717275 cites W2003128044 @default.
• W4378717275 cites W2026404834 @default.
• W4378717275 cites W2052130492 @default.
• W4378717275 cites W2056972873 @default.
• W4378717275 cites W2070644850 @default.
• W4378717275 cites W2078443730 @default.
• W4378717275 cites W2092017766 @default.
• W4378717275 cites W2113693127 @default.
• W4378717275 cites W2125736318 @default.
• W4378717275 cites W2143890359 @default.
• W4378717275 cites W2144364061 @default.
• W4378717275 cites W2147536372 @default.
• W4378717275 cites W2150486005 @default.
• W4378717275 cites W2154497083 @default.
• W4378717275 cites W2156527216 @default.
• W4378717275 cites W2158997610 @default.
• W4378717275 cites W2178644161 @default.
• W4378717275 cites W2250539671 @default.
• W4378717275 cites W2276520418 @default.
• W4378717275 cites W2493916176 @default.
• W4378717275 cites W2550484220 @default.
• W4378717275 cites W2580240408 @default.
• W4378717275 cites W2604132829 @default.
• W4378717275 cites W2605389422 @default.
• W4378717275 cites W2607788147 @default.
• W4378717275 cites W2758300063 @default.
• W4378717275 cites W2789706137 @default.
• W4378717275 cites W2791063712 @default.
• W4378717275 cites W2802065111 @default.
• W4378717275 cites W2805123274 @default.
• W4378717275 cites W2806168354 @default.
• W4378717275 cites W2879234625 @default.
• W4378717275 cites W2886745660 @default.
• W4378717275 cites W2889886504 @default.
• W4378717275 cites W2951189123 @default.
• W4378717275 cites W2970641574 @default.
• W4378717275 cites W2979826702 @default.
• W4378717275 cites W3008435479 @default.
• W4378717275 cites W3016737495 @default.
• W4378717275 cites W3034723486 @default.
• W4378717275 cites W3048783167 @default.
• W4378717275 cites W3059654161 @default.
• W4378717275 cites W3083285628 @default.
• W4378717275 cites W3084211362 @default.
• W4378717275 cites W3100307207 @default.
• W4378717275 cites W3103536442 @default.
• W4378717275 cites W3128571582 @default.
• W4378717275 cites W3154770621 @default.
• W4378717275 cites W3161283304 @default.
• W4378717275 cites W3185049111 @default.
• W4378717275 cites W3198881445 @default.
• W4378717275 cites W3208539668 @default.
• W4378717275 cites W4206346522 @default.
• W4378717275 cites W4210452949 @default.
• W4378717275 cites W4220949944 @default.
• W4378717275 cites W4226119767 @default.
• W4378717275 cites W4244249510 @default.
• W4378717275 cites W4280523169 @default.
• W4378717275 cites W4285011939 @default.
• W4378717275 cites W4289222848 @default.
• W4378717275 cites W4290097556 @default.
• W4378717275 cites W4312129600 @default.
• W4378717275 cites W1977002346 @default.
• W4378717275 cites W2962998311 @default.
• W4378717275 doi "https://doi.org/10.1016/j.bpsc.2023.05.005" @default.
• W4378717275 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37257754" @default.
• W4378717275 hasPublicationYear "2023" @default.
• W4378717275 type Work @default.
• W4378717275 citedByCount "0" @default.
• W4378717275 crossrefType "journal-article" @default.
• W4378717275 hasAuthorship W4378717275A5044364722 @default.
• W4378717275 hasAuthorship W4378717275A5069337982 @default.
• W4378717275 hasAuthorship W4378717275A5073964938 @default.
• W4378717275 hasBestOaLocation W43787172751 @default.
• W4378717275 hasConcept C137293760 @default.
• W4378717275 hasConcept C151730666 @default.
• W4378717275 hasConcept C154945302 @default.
• W4378717275 hasConcept C15744967 @default.
• W4378717275 hasConcept C169760540 @default.
• W4378717275 hasConcept C169900460 @default.

• next