Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210151771> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W3210151771 abstract "Deep-learning based language models (LMs) have significantly enhanced services relating to language generation and classification. Our focus in this paper is on the Multiple Mini Interview (MMI) which is commonly used internationally by medical schools to screen applicants based on their ability to answer short questions in a considerate, professional manner. In this paper we establish the ability of LMs, specifically GPT-3, to generate MMI questions, simulate responses, and rate answers. We compare these simulated questions with their human generated counterparts and, after identifying the optimal hyperparameters, find that 92% of generated responses are capable of fooling humans. We also find that after identifying the optimal hyperparameters for question-answering, LMs are capable producing high quality simulated MMI responses, with an average human rating of 3.5 out of 5. Finally, GPT-3 is shown to have some agreement with human ratings, although it tends to overestimate the quality of the response. Conditional text generation by LMs alone seems to be able to significantly support MMI preparation." @default.
- W3210151771 created "2021-11-08" @default.
- W3210151771 creator A5042070897 @default.
- W3210151771 creator A5049218176 @default.
- W3210151771 date "2021-08-25" @default.
- W3210151771 modified "2023-09-26" @default.
- W3210151771 title "Support for Interview Preparation with Deep Learning Based Language Model" @default.
- W3210151771 cites W2035565684 @default.
- W3210151771 cites W207841007 @default.
- W3210151771 cites W2115466947 @default.
- W3210151771 cites W2140015094 @default.
- W3210151771 cites W2329538042 @default.
- W3210151771 cites W2783447860 @default.
- W3210151771 cites W2900607085 @default.
- W3210151771 cites W2911122285 @default.
- W3210151771 cites W2943922504 @default.
- W3210151771 cites W2963403868 @default.
- W3210151771 cites W3030163527 @default.
- W3210151771 cites W3118854552 @default.
- W3210151771 cites W650350307 @default.
- W3210151771 doi "https://doi.org/10.1109/icetci51973.2021.9574063" @default.
- W3210151771 hasPublicationYear "2021" @default.
- W3210151771 type Work @default.
- W3210151771 sameAs 3210151771 @default.
- W3210151771 citedByCount "0" @default.
- W3210151771 crossrefType "proceedings-article" @default.
- W3210151771 hasAuthorship W3210151771A5042070897 @default.
- W3210151771 hasAuthorship W3210151771A5049218176 @default.
- W3210151771 hasConcept C108583219 @default.
- W3210151771 hasConcept C111472728 @default.
- W3210151771 hasConcept C119857082 @default.
- W3210151771 hasConcept C120665830 @default.
- W3210151771 hasConcept C121332964 @default.
- W3210151771 hasConcept C138885662 @default.
- W3210151771 hasConcept C154945302 @default.
- W3210151771 hasConcept C192209626 @default.
- W3210151771 hasConcept C204321447 @default.
- W3210151771 hasConcept C2779530757 @default.
- W3210151771 hasConcept C41008148 @default.
- W3210151771 hasConcept C8642999 @default.
- W3210151771 hasConceptScore W3210151771C108583219 @default.
- W3210151771 hasConceptScore W3210151771C111472728 @default.
- W3210151771 hasConceptScore W3210151771C119857082 @default.
- W3210151771 hasConceptScore W3210151771C120665830 @default.
- W3210151771 hasConceptScore W3210151771C121332964 @default.
- W3210151771 hasConceptScore W3210151771C138885662 @default.
- W3210151771 hasConceptScore W3210151771C154945302 @default.
- W3210151771 hasConceptScore W3210151771C192209626 @default.
- W3210151771 hasConceptScore W3210151771C204321447 @default.
- W3210151771 hasConceptScore W3210151771C2779530757 @default.
- W3210151771 hasConceptScore W3210151771C41008148 @default.
- W3210151771 hasConceptScore W3210151771C8642999 @default.
- W3210151771 hasFunder F4320306076 @default.
- W3210151771 hasLocation W32101517711 @default.
- W3210151771 hasOpenAccess W3210151771 @default.
- W3210151771 hasPrimaryLocation W32101517711 @default.
- W3210151771 hasRelatedWork W3107474891 @default.
- W3210151771 hasRelatedWork W4223943233 @default.
- W3210151771 hasRelatedWork W4281616679 @default.
- W3210151771 hasRelatedWork W4283697347 @default.
- W3210151771 hasRelatedWork W4295309597 @default.
- W3210151771 hasRelatedWork W4298144215 @default.
- W3210151771 hasRelatedWork W4307195028 @default.
- W3210151771 hasRelatedWork W4312200629 @default.
- W3210151771 hasRelatedWork W4360585206 @default.
- W3210151771 hasRelatedWork W4364306694 @default.
- W3210151771 isParatext "false" @default.
- W3210151771 isRetracted "false" @default.
- W3210151771 magId "3210151771" @default.
- W3210151771 workType "article" @default.