基于迁移学习的地理领域概念关系抽取

来源 :第十六届全国计算语言学学术会议暨第五届基于自然标注大数据的自然语言处理国际学术研讨会 | 被引量 : 0次 | 上传用户：kanshu

【摘要】

：

在地理等特有领域概念关系抽取过程中,由于其有限的样本标注资源,难以应用深度学习等大规模知识图谱构建技术.迁移学习方法能够利用开放域文本语料资源,帮助解决目标领域训练数据较少的问题.本文针对地理领域文本的时序性特征,利用长短期记忆(LongShort-Term Memory,LSTM)神经网络,构建了基于词特征和句子特征的概念关系抽取模型,针对地理概念关系语料缺乏的问题,提出了基于LSTM的迁移学习

【作者】

：

熊盛武陈振东段鹏飞王娜

【机构】

：

武汉理工大学计算机科学与技术学院,武汉 430070;交通物联网湖北省重点实验室,武汉 430070

【出处】

：

第十六届全国计算语言学学术会议暨第五届基于自然标注大数据的自然语言处理国际学术研讨会

【发表日期】

：

2017年7期

【关键词】

：

地理领域概念关系抽取迁移学习

下载到本地 , 更方便阅读

下载此文赞助VIP

声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架

论文部分内容阅读

其他文献

分散式电采暖负荷协同优化运行策略研究

利用电采暖大规模、成区域地实现供暖电能替代，可有效缓解我国北方的供暖性雾霾。分散式的电采暖负荷是一种典型的热储能设备，功率较大，电能产出的热量具有滞后性和存储性，现有运行方式单一且仅针对单个设备，无法实现区域范围内电采暖设备的协同优化。本文首先提出了智能电暖网络的概念、架构，以及衡量该网络运行效果的优化指标。其次，提出了智能电暖网络的确定性优化运行模型，该模型首先在保证最大功率限制的约束下，求解可

会议

智能用电网络电采暖负荷调度需求响应

Flexible unbalanced control with peak current limitation for virtual synchronous generator under vol

Virtual synchronous generator(VSG)is grid-friendly for integrating distributed generations(DGs)since it can emulate the operation mechanism of traditional synchronous generator(SG).However,the traditi

会议

Virtual synchronous generatorUnbalanced controlCurrent reference generatorPow

Impact of Power System Network Topology Errors on Real-Time Locational Marginal Price

This paper examines the impact of power transmission network topology change on locational marginal price(LMP)in real-time power markets.We consider the case where the false status of circuit breakers

会议

Power marketEconomic dispatchLocational marginal pricePower system network to

An Optimal Design of Hybrid Wind/Photovoltaic Electrolyzer for Maximum Hydrogen Production Using Imp

The rising demand for high density power storage systems such as hydrogen,combined with renewable power production systems,has led to the design of optimal power production and storage systems.In this

会议

ElectrolyzerHydrogenWind TurbinePhotovoltaicICA

Agent-based simulation for symmetric electricity market considering price-based demand response

With the development of electricity market mechanism and advanced metering infrastructure(AMI),demand response has become an important alternative solution to improving power system reliability and ef

会议

Agent-based simulationTrading mechanismDemand responseElectricity market

Economic optimization for configuration and sizing of micro integrated energy systems

Based on analysis of construction and operation of micro integrated energy systems(MIES),this paper presents economic optimization for their configuration and sizing.After presenting typical models fo

会议

Micro integrated energy system (MIES)Economic optimizationUncertaintiesNon-do

Long-term system load forecasting based on a data-driven linear clustering method

In this paper,a data-driven linear clustering(DLC)method is proposed to solve the long-term system load forecasting problem caused by load fluctuation in some developed cities.A large substation load

会议

Long-term system load forecastingData-drivenLinear clusteringAutoregressive i

A robust optimization method for energy management of CCHP microgrid

Energy management is facing new challenges due to the increasing supply and demand uncertainties,which is caused by the integration of variable generation resources,inaccurate load forecasts and non-l

会议

Combined coolingHeating and power (CCHP)MicrogridPiecewise linearRobust opti

Transmission congestion tracing technique and its application to recognize weak parts of bulk power

A bulk power system is conventionally characterized by a complex structure with a large number of components.Each component generally has a different contribution to the transmission congestion(TC)of

会议

Transmission congestionCongestion indicesCongestion tracing principleComponen

浅谈酶制剂在速冻油条生胚中的应用

本文研究了几种酶制剂在速冻油条生胚中的-些应用,为油条工业化大生产企业技术人员在使用酶制剂时提供一些参考和帮助.试验表明:酶制剂对改善速冻油条生胚的抗冻性能有一定效果.

会议

速冻油条生胚制作酶制剂抗冻性能

基于迁移学习的地理领域概念关系抽取

与本文相关的学术论文