Uncertainty-Aware Self-Training for Semi-Supervised Event Temporal Relation Extraction
文献类型:会议论文
作者 | Pengfei Cao1,2; Xinyu Zuo1,3; Yubo Chen1,2; Kang Liu1,2; Jun Zhao1,2; Wei Bi1,3 |
出版日期 | 2021-11-01 |
会议日期 | November 1–5, 2021 |
会议地点 | Virtual Event, QLD, Australia |
英文摘要 | Extracting event temporal relations is an important task for natural language understanding. Many works have been proposed for supervised event temporal relation extraction, which typically requires a large amount of human-annotated data for model training. However, the data annotation for this task is very time-consuming and challenging. To this end, we study the problem of semi-supervised event temporal relation extraction. Self-training as a widely used semi-supervised learning method can be utilized for this problem. However, it suffers from the noisy pseudo-labeling problem. In this paper, we propose the use of uncertainty-aware self-training framework (UAST) to quantify the model uncertainty for coping with pseudo-labeling errors. Specifically, UAST utilizes (1) Uncertainty Estimation module to compute the model uncertainty for pseudo-labeling unlabeled data; (2) Sample Selection with Exploration module to select informative samples based on uncertainty estimates; and (3) Uncertainty-Aware Learning module to explicitly incorporate the model uncertainty into the self-training process. Experimental results indicate that our approach significantly outperforms previous state-of-the-art methods. |
源URL | [http://ir.ia.ac.cn/handle/173211/52184] |
专题 | 模式识别国家重点实验室_自然语言处理 |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, CAS 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Tencent |
推荐引用方式 GB/T 7714 | Pengfei Cao,Xinyu Zuo,Yubo Chen,et al. Uncertainty-Aware Self-Training for Semi-Supervised Event Temporal Relation Extraction[C]. 见:. Virtual Event, QLD, Australia. November 1–5, 2021. |
入库方式: OAI收割
来源:自动化研究所
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。