QQ客服 官方微博 反馈留言

	Improving First Order Temporal Fact Extraction with Unreliable Data
	Luo, Bingfeng ; Feng, Yansong ; Wang, Zheng ; Zhao, Dongyan
	2016
关键词	Temporal fact extraction Distant supervision Knowledge base
英文摘要	In this paper, we deal with the task of extracting first order temporal facts from free text. This task is a subtask of relation extraction and it aims at extracting relations between entity and time. Currently, the field of relation extraction mainly focuses on extracting relations between entities. However, we observe that the multi-granular nature of time expressions can help us divide the dataset constructed by distant supervision into reliable and less reliable subsets, which can help to improve the extraction results on relations between entity and time. We accordingly contribute the first dataset focusing on the first order temporal fact extraction task using distant supervision. To fully utilize both the reliable and the less reliable data, we propose to use curriculum learning to rearrange the training procedure, label dropout to make the model be more conservative about less reliable data, and instance attention to help the model distinguish important instances from unimportant ones. Experiments show that these methods help the model outperform the model trained purely on the reliable dataset as well as the model trained on the dataset where all subsets are mixed together.; National High Technology R&D Program of China [2015AA015403, 2014AA015102]; Natural Science Foundation of China [61202233, 61272344, 61370055]; IBM Research; CPCI-S(ISTP); 251-262; 10102
语种	英语
出处	5th International Conference on Natural Language Processing and Chinese Computing (NLPCC) / 24th International Conference on Computer Processing of Oriental Languages (ICCPOL)
DOI标识	10.1007/978-3-319-50496-4_21
内容类型	其他
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/470113]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Luo, Bingfeng,Feng, Yansong,Wang, Zheng,et al. Improving First Order Temporal Fact Extraction with Unreliable Data. 2016-01-01.

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。