Knowledge Commons of Institute of Automation,CAS
Augmenting Slot Values and Contexts for Spoken Language Understanding with Pretrained Models | |
Lin, Haitao1,2![]() ![]() ![]() ![]() ![]() | |
2021-09 | |
会议名称 | Interspeech 2021 |
会议录名称 | Proceedings of Interspeech 2021 |
页码 | 4703-4707 |
会议日期 | 2021-08-30 - 2021-09-03 |
会议地点 | Brno, Czechia |
摘要 | Spoken Language Understanding (SLU) is one essential step in building a dialogue system. Due to the expensive cost of obtaining the labeled data, SLU suffers from the data scarcity problem. Therefore, in this paper, we focus on data augmentation for slot filling task in SLU. To achieve that, we aim at generating more diverse data based on existing data. Specifically, we try to exploit the latent language knowledge from pretrained language models by finetuning them. We propose two strategies for finetuning process: value-based and context-based augmentation. Experimental results on two public SLU datasets have shown that compared with existing data augmentation methods, our proposed method can generate more diverse sentences and significantly improve the performance on SLU. |
收录类别 | EI |
语种 | 英语 |
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/173211/51973 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
通讯作者 | Zhou, Yu |
作者单位 | 1.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, China 3.Fanyu AI Laboratory, Beijing Fanyu Technology Co., Ltd, Beijing, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Lin, Haitao,Xiang, Lu,Zhou, Yu,et al. Augmenting Slot Values and Contexts for Spoken Language Understanding with Pretrained Models[C],2021:4703-4707. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
55_Paper.pdf(222KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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