ACL Findings2023
Medical Dialogue Generation via Dual Flow Modeling
Kaishuai Xu, Wenjun Hou, Yi Cheng, Jian Wang, Wenjie Li
Abstract
Medical dialogue systems (MDS) aim to provide patients with medical services, such as diagnosis and prescription.Since most patients cannot precisely describe their symptoms, dialogue understanding is challenging for MDS.Previous studies mainly addressed this by extracting the mentioned medical entities as critical dialogue history information.In this work, we argue that it is also essential to capture the transitions of the medical entities and the doctor's dialogue acts in each turn, as they help the understanding of how the dialogue flows and enhance the prediction of the entities and dialogue acts to be adopted in the following turn.Correspondingly, we propose a Dual Flow enhanced Medical (DFMED) dialogue generation framework.It extracts the medical entities and dialogue acts used in the dialogue history and models their transitions with an entity-centric graph flow and a sequential act flow, respectively.We employ two sequential models to encode them and devise an interweaving component to enhance their interactions.Experiments on two datasets demonstrate that our method exceeds baselines in both automatic and manual evaluations. 1) Pa#ent: I had a stomachache in the a+ernoon the day before yesterday and then started vomi#ng and had diarrhoea at night.A+er drinking four tubes of Huoxiang Zhengqi water, I s8ll vomit and can't eat.2) Doctor: Hello, I am glad to answer your ques8ons!Where exactly is the stomachache?👨⚕ 🙍 Act Flow … 8) Doctor: You may have acute gastroenteri#s.It is recommended to take Omeprazole, Mosapride and Bifidobacterium tablets.👨⚕ 9) Pa#ent: But I had acute gastroenteri#s before.The stomachache was extremely severe last 8me, while this 8me, it was not.Is that reasonable?🙍 10) Doctor: Yeah.The stomachache caused by gastroenteri#s can be of different degrees.👨⚕ 3) Pa#ent: Below navel.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on8
- SimCSE: Simple Contrastive Learning of Sentence EmbeddingsTianyu Gao, Xingcheng Yao, Danqi ChenEMNLP 2021 · 2,496 citations
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
- MedDialog: Large-scale Medical Dialogue DatasetsGuangtao Zeng, Wenmian Yang, Zeqian Ju, Yue Yang et al.EMNLP 2020 · 163 citations
- Generative Adversarial Regularized Mutual Information Policy Gradient Framework for Automatic DiagnosisYuan Xia, Jingbo Zhou, Zhenhui Shi, Chao Lu et al.AAAI 2020 · 85 citations
- Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue GenerationShuai Lin, Pan Zhou, Xiaodan Liang, Jianheng Tang et al.AAAI 2021 · 66 citations
Related papers
- Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt AdjustmentHongda Sun, Jiaren Peng, Wenzhong Yang, Liang He et al.ACL Findings 2025
- Reasoning Like a Doctor: Improving Medical Dialogue Systems via Diagnostic Reasoning Process AlignmentKaishuai Xu, Yi Cheng, Wenjun Hou, Qiaoyu Tan et al.ACL Findings 2024 · 7 citations
- CDialog: A Multi-turn Covid-19 Conversation Dataset for Entity-Aware Dialog GenerationDeeksha Varshney, Aizan Zafar, Niranshu Kumar Behra, Asif EkbalEMNLP 2022 · 2 citations
- MIE: A Medical Information Extractor towards Medical DialoguesYuanzhe Zhang, Zhongtao Jiang, Tao Zhang, Shiwan Liu et al.ACL 2020 · 48 citations
- Listening to Patients: Detecting and Mitigating Patient Misreport in Medical Dialogue SystemLang Qin, Yao Zhang, Hongru Liang, Adam Jatowt et al.ACL Findings 2025 · 2 citations
