Matches in SemOpenAlex for { <https://semopenalex.org/work/W3025853514> ?p ?o ?g. }
- W3025853514 abstract "Under the pandemic of COVID-19, people experiencing COVID19-related symptoms or exposed to risk factors have a pressing need to consult doctors. Due to hospital closure, a lot of consulting services have been moved online. Because of the shortage of medical professionals, many people cannot receive online consultations timely. To address this problem, we aim to develop a medical dialogue system that can provide COVID19-related consultations. We collected two dialogue datasets -- CovidDialog -- (in English and Chinese respectively) containing conversations between doctors and patients about COVID-19. On these two datasets, we train several dialogue generation models based on Transformer, GPT, and BERT-GPT. Since the two COVID-19 dialogue datasets are small in size, which bear high risk of overfitting, we leverage transfer learning to mitigate data deficiency. Specifically, we take the pretrained models of Transformer, GPT, and BERT-GPT on dialog datasets and other large-scale texts, then finetune them on our CovidDialog tasks. We perform both automatic and human evaluation of responses generated by these models. The results show that the generated responses are promising in being doctor-like, relevant to the conversation history, and clinically informative. The data and code are available at https://github.com/UCSD-AI4H/COVID-Dialogue." @default.
- W3025853514 created "2020-05-21" @default.
- W3025853514 creator A5000958452 @default.
- W3025853514 creator A5009547049 @default.
- W3025853514 creator A5018866860 @default.
- W3025853514 creator A5019284302 @default.
- W3025853514 creator A5052225474 @default.
- W3025853514 creator A5056066703 @default.
- W3025853514 creator A5061025828 @default.
- W3025853514 creator A5073017662 @default.
- W3025853514 creator A5079794774 @default.
- W3025853514 creator A5083884675 @default.
- W3025853514 creator A5085729267 @default.
- W3025853514 creator A5087935332 @default.
- W3025853514 date "2020-05-11" @default.
- W3025853514 modified "2023-09-28" @default.
- W3025853514 title "On the Generation of Medical Dialogues for COVID-19" @default.
- W3025853514 cites W1522301498 @default.
- W3025853514 cites W1924770834 @default.
- W3025853514 cites W2043884036 @default.
- W3025853514 cites W2064675550 @default.
- W3025853514 cites W2078861931 @default.
- W3025853514 cites W2101105183 @default.
- W3025853514 cites W2130942839 @default.
- W3025853514 cites W2133512280 @default.
- W3025853514 cites W2194775991 @default.
- W3025853514 cites W2328886022 @default.
- W3025853514 cites W2504052070 @default.
- W3025853514 cites W2588443021 @default.
- W3025853514 cites W2623779865 @default.
- W3025853514 cites W2743233975 @default.
- W3025853514 cites W2763552934 @default.
- W3025853514 cites W2843010082 @default.
- W3025853514 cites W2886305736 @default.
- W3025853514 cites W2890969459 @default.
- W3025853514 cites W2903928064 @default.
- W3025853514 cites W2962784628 @default.
- W3025853514 cites W2963206148 @default.
- W3025853514 cites W2963341956 @default.
- W3025853514 cites W2963403868 @default.
- W3025853514 cites W2965373594 @default.
- W3025853514 cites W2982399380 @default.
- W3025853514 cites W2992922049 @default.
- W3025853514 cites W3037026762 @default.
- W3025853514 cites W3210120707 @default.
- W3025853514 doi "https://doi.org/10.48550/arxiv.2005.05442" @default.
- W3025853514 hasPublicationYear "2020" @default.
- W3025853514 type Work @default.
- W3025853514 sameAs 3025853514 @default.
- W3025853514 citedByCount "5" @default.
- W3025853514 countsByYear W30258535142020 @default.
- W3025853514 countsByYear W30258535142021 @default.
- W3025853514 crossrefType "posted-content" @default.
- W3025853514 hasAuthorship W3025853514A5000958452 @default.
- W3025853514 hasAuthorship W3025853514A5009547049 @default.
- W3025853514 hasAuthorship W3025853514A5018866860 @default.
- W3025853514 hasAuthorship W3025853514A5019284302 @default.
- W3025853514 hasAuthorship W3025853514A5052225474 @default.
- W3025853514 hasAuthorship W3025853514A5056066703 @default.
- W3025853514 hasAuthorship W3025853514A5061025828 @default.
- W3025853514 hasAuthorship W3025853514A5073017662 @default.
- W3025853514 hasAuthorship W3025853514A5079794774 @default.
- W3025853514 hasAuthorship W3025853514A5083884675 @default.
- W3025853514 hasAuthorship W3025853514A5085729267 @default.
- W3025853514 hasAuthorship W3025853514A5087935332 @default.
- W3025853514 hasBestOaLocation W30258535141 @default.
- W3025853514 hasConcept C119857082 @default.
- W3025853514 hasConcept C121332964 @default.
- W3025853514 hasConcept C136764020 @default.
- W3025853514 hasConcept C138885662 @default.
- W3025853514 hasConcept C142724271 @default.
- W3025853514 hasConcept C150899416 @default.
- W3025853514 hasConcept C153083717 @default.
- W3025853514 hasConcept C154945302 @default.
- W3025853514 hasConcept C15744967 @default.
- W3025853514 hasConcept C165801399 @default.
- W3025853514 hasConcept C173853756 @default.
- W3025853514 hasConcept C17744445 @default.
- W3025853514 hasConcept C194051981 @default.
- W3025853514 hasConcept C199539241 @default.
- W3025853514 hasConcept C204321447 @default.
- W3025853514 hasConcept C22019652 @default.
- W3025853514 hasConcept C2777200299 @default.
- W3025853514 hasConcept C2778137410 @default.
- W3025853514 hasConcept C2778757428 @default.
- W3025853514 hasConcept C2779134260 @default.
- W3025853514 hasConcept C3008058167 @default.
- W3025853514 hasConcept C41008148 @default.
- W3025853514 hasConcept C41895202 @default.
- W3025853514 hasConcept C46312422 @default.
- W3025853514 hasConcept C50644808 @default.
- W3025853514 hasConcept C524204448 @default.
- W3025853514 hasConcept C62520636 @default.
- W3025853514 hasConcept C66322947 @default.
- W3025853514 hasConcept C71924100 @default.
- W3025853514 hasConceptScore W3025853514C119857082 @default.
- W3025853514 hasConceptScore W3025853514C121332964 @default.
- W3025853514 hasConceptScore W3025853514C136764020 @default.
- W3025853514 hasConceptScore W3025853514C138885662 @default.
- W3025853514 hasConceptScore W3025853514C142724271 @default.