Medical Term and Status Generation From Chinese Clinical Dialogue With Multi-Granularity Transformer
文献类型：期刊论文
| 作者 | Li, Mei1,2 ; Xiang, Lu1,2; Kang, Xiaomian1,2; Zhao, Yang1,2; Zhou, Yu1,3,4; Zong, Chengqing1,5
|
| 刊名 | IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
 |
| 出版日期 | 2021 |
| 卷号 | 29页码:3362-3374 |
| 关键词 | Medical diagnostic imaging Transformers Task analysis Medical services Computational modeling Semantics Data mining Medical dialogue multi-granularity attention mechanism natural language understanding sequence to sequence learning |
| ISSN号 | 2329-9290 |
| DOI | 10.1109/TASLP.2021.3122301 |
| 通讯作者 | Zong, Chengqing(cqzong@nlpr.ia.ac.cn) |
| 英文摘要 | This paper describes a generative model for extracting medical terms and their status from Chinese medical dialogues. Notably, the extracted semantic information is particularly important to downstream tasks like automatic medical scribe and automatic diagnosis systems. However, how to effectively leverage dialogue context to generate medical terms and their corresponding status accurately remains less explored. Existing generative approaches treat dialogue text as a single continuous text, ignoring conversational characteristics like colloquialism, redundancy and interactions. Between the doctor and the patient, a variety of colloquial medical information is frequently discussed. Each speaker (doctor and patient) plays a specific role in the interaction's goals. As a result, the importance of role information and interactions between utterances cannot be overstated. Furthermore, existing generative approaches only use character-level tokens, disregarding word-level tokens, which are the shortest meaningful utterances in Chinese. In this paper, we propose a Multi-granularity Transformer (MGT) model to enhance the dialogue context understanding from multi-granularity features. We incorporate word-level information by adapting a Lattice-based encoder with our proposed relative position encoding method. We further propose a Role Access Controlled Attention (RaCa) mechanism for introducing utterance-level interaction information. Experimental results on two benchmark datasets illustrate our model's validity and effectiveness, achieving state-of-the-art performance on both datasets. |
| 资助项目 | National Key R&D Program of China[2020AAA0108600] |
| WOS研究方向 | Acoustics ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000716689200004 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Key R&D Program of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/46328]  |
| 专题 | 模式识别国家重点实验室_自然语言处理 |
| 通讯作者 | Zong, Chengqing |
| 作者单位 | 1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci CAS, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 4.Beijing Fanyu Technol Co Ltd, Fanyu AI Lab, Beijing, Peoples R China 5.CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 200031, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Mei,Xiang, Lu,Kang, Xiaomian,et al. Medical Term and Status Generation From Chinese Clinical Dialogue With Multi-Granularity Transformer[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,2021,29:3362-3374. |
| APA | Li, Mei,Xiang, Lu,Kang, Xiaomian,Zhao, Yang,Zhou, Yu,&Zong, Chengqing.(2021).Medical Term and Status Generation From Chinese Clinical Dialogue With Multi-Granularity Transformer.IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,29,3362-3374. |
| MLA | Li, Mei,et al."Medical Term and Status Generation From Chinese Clinical Dialogue With Multi-Granularity Transformer".IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 29(2021):3362-3374. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。