Knowledge Commons of Institute of Automation,CAS
Matching-based Term Semantics Pre-training for Spoken Patient Query Understanding | |
Zefa Hu1,2![]() ![]() ![]() ![]() ![]() ![]() ![]() | |
2023-06-06 | |
会议名称 | IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023 |
会议日期 | 2023-6-6 - 2023-6-10 |
会议地点 | Rhodes, Greece |
摘要 | Medical Slot Filling (MSF) task aims to convert medical queries into structured information, playing an essential role in diagnosis dialogue systems. However, the lack of sufficient term semantics learning makes existing approaches hard to capture semantically identical but colloquial expressions of terms in medical conversations. In this work, we formalize MSF into a matching problem and propose a Term Semantics Pre-trained Matching Network (TSPMN) that takes both terms and queries as input to model their semantic interaction. To learn term semantics better, we further design two self-supervised objectives, including Contrastive Term Discrimination (CTD) and Matching-based Mask Term Modeling (MMTM). CTD determines whether it is the masked term in the dialogue for each given term, while MMTM directly predicts the masked ones. Experimental results on two Chinese benchmarks show that TSPMN outperforms strong |
收录类别 | EI |
资助项目 | Chinese Academy of Science[QYZDB-SSW-JSC006] ; Chinese Academy of Science[QYZDB-SSW-JSC006] |
七大方向——子方向分类 | 自然语言处理 |
国重实验室规划方向分类 | 语音语言处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/56683 |
专题 | 复杂系统认知与决策实验室_听觉模型与认知计算 |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.Institute of Automation, Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zefa Hu,Xiuyi Chen,Haoran Wu,et al. Matching-based Term Semantics Pre-training for Spoken Patient Query Understanding[C],2023. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
icassp.pdf(1049KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论