Knowledge Commons of Institute of Automation,CAS
Focal Loss for Punctuation Prediction | |
Jiangyan Yi; Jianhua Tao; Zhengkun Tian; Ye Bai; Cunhang Fan | |
2020 | |
会议名称 | 21th Annual Conference of the International Speech Communication Association(Interspeech 2020) |
会议日期 | 2020.10.25-2020.10.29 |
会议地点 | 北京,中国 |
摘要 | Many approaches have been proposed to predict punctuation marks. Previous results demonstrate that these methods are effective. However, there still exists class imbalance problem during training. Most of the classes in the training set for punctuation prediction are non-punctuation marks. This will affect the performance of punctuation prediction tasks. Therefore, this paper uses a focal loss to alleviate this issue. The focal loss can down-weight easy examples and focus training on a sparse set of hard examples. Experiments are conducted on IWSLT2011 datasets. The results show that the punctuation predicting models trained with a focal loss obtain performance improvement over that trained with a cross entropy loss by up to 2.7% absolute overall F1-score on test set. The proposed model also outperforms previous state-of-the-art models. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 语音识别与合成 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40664 |
专题 | 多模态人工智能系统全国重点实验室_智能交互 |
作者单位 | 1.中国科学院自动化研究所; 2.中国科学院大学 |
推荐引用方式 GB/T 7714 | Jiangyan Yi,Jianhua Tao,Zhengkun Tian,et al. Focal Loss for Punctuation Prediction[C],2020. |
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 | ||
interspeech 2020 Mon(247KB) | 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