Focal Loss for Punctuation Prediction | |
Jiangyan Yi; Jianhua Tao; Zhengkun Tian; Ye Bai; Cunhang Fan | |
2020 | |
会议日期 | 2020.10.25-2020.10.29 |
会议地点 | 北京,中国 |
英文摘要 | 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. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/40664] |
专题 | 模式识别国家重点实验室_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]. 见:. 北京,中国. 2020.10.25-2020.10.29. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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