Medical Dialogue Task
(Redirected from medical dialogue task)
Jump to navigation
Jump to search
A Medical Dialogue Task is a dialogue task that involves medical tasks.
- Context:
- It can be instantiated in a Medical Dialogue Instance.
- It can be associated with a Medical Dialogue Dataset.
- It can be a Medical Information Capturing Task, ...
- …
- See: Medical Q&A, Medical Dialogue System, Medical Diagnosis Task.
References
2020
- (Zeng et al., 2020) ⇒ Guangtao Zeng, Wenmian Yang, Zeqian Ju, Yue Yang, Sicheng Wang, Ruisi Zhang, Meng Zhou et al. (2020). “MedDialog: Large-scale Medical Dialogue Dataset.” In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).
- ABSTRACT: Medical dialogue systems are promising in assisting in telemedicine to increase access to healthcare services, improve the quality of patient care, and reduce medical costs. To facilitate the research and development of medical dialogue systems, we build large-scale medical dialogue datasets – MedDialog, which contain 1) a Chinese dataset with 3.4 million conversations between patients and doctors, 11.3 million utterances, 660.2 million tokens, covering 172 specialties of diseases, and 2) an English dataset with 0.26 million conversations, 0.51 million utterances, 44.53 million tokens, covering 96 specialties of diseases. To our best knowledge, MedDialog is the largest medical dialogue dataset to date. We pretrain several dialogue generation models on the Chinese MedDialog dataset, including Transformer, GPT, BERT-GPT, and compare their performance. It is shown that models trained on MedDialog are able to generate clinically correct and doctor-like medical dialogues. We also study the transferability of models trained on MedDialog to low-resource medical dialogue generation tasks. It is shown that via transfer learning which finetunes the models pretrained on MedDialog, the performance on medical dialogue generation tasks with small datasets can be greatly improved, as shown in human evaluation and automatic evaluation. The datasets and code are available at https://github.com/UCSD-AI4H/Medical-Dialogue-System
1992
- (Roter & Frankel, 1992) ⇒ Debra Roter, and Richard Frankel. (1992). “Quantitative and Qualitative Approaches to the Evaluation of the Medical Dialogue.” Social Science & Medicine, 34(10).
- ABSTRACT: Increasing availability of audio and videotape of medical encounters has drawn the attention of researchers from diverse disciplines and perspectives. Unfortunately, the result has more frequently been interdisciplinary competition than collaboration. Most striking are the differences in approach between researchers applying qualitative and quantitative methods. Advocates of each of these methods have not only argued their own relative merits, but have maintained unusually critical and intellectually isolated positions.
The purpose of this paper is to demonstrate that the paradigmatic perspective which promotes mutual exclusivity is in error. We present several examples of research findings which demonstrate the rich potential for cross-method research. Examples have been taken from the areas of most fruitful qualitative and quantitative research—information gathering, patient disclosure, and information-giving.
- ABSTRACT: Increasing availability of audio and videotape of medical encounters has drawn the attention of researchers from diverse disciplines and perspectives. Unfortunately, the result has more frequently been interdisciplinary competition than collaboration. Most striking are the differences in approach between researchers applying qualitative and quantitative methods. Advocates of each of these methods have not only argued their own relative merits, but have maintained unusually critical and intellectually isolated positions.