IEEE知识和数据工程事务TKDE(IEEE Transactions on Knowledge and Data Engineering)向研究人员、开发人员、管理人员、战略规划人员等用户和其他对知识和数据工程领域的最新活动和实践活动感兴趣的人员提供信息。官网地址:http://dblp.uni-trier.de/db/journals/tkde/

VIP内容

命名实体识别(NER)的任务是识别提到命名实体的文本范围,并将它们分类为预定义的类别,如人员、位置、组织等。NER是各种自然语言应用的基础,如问题回答、文本摘要和机器翻译。虽然早期的NER系统能够成功地产生相当高的识别精度,但它们通常需要大量的人力来精心设计规则或特征。近年来,基于连续实值向量表示和通过非线性处理的语义组合的深度学习被应用到NER系统中,产生了最先进的性能。在这篇论文中,我们对现有的深度学习技术进行了全面的回顾。我们首先介绍NER资源,包括标记的NER语料库和现成的NER工具。然后,我们根据一个分类法沿着三个轴对现有的作品进行了系统的分类:输入的分布式表示、上下文编码器和标记解码器。接下来,我们调查了最近在新的NER问题设置和应用中应用深度学习技术的最有代表性的方法。最后,我们向读者介绍NER系统所面临的挑战,并概述该领域的未来发展方向。

成为VIP会员查看完整内容
0
34

最新论文

Node connectivity plays a central role in temporal network analysis. We provide a comprehensive study of various concepts of walks in temporal graphs, that is, graphs with fixed vertex sets but edge sets changing over time. Taking into account the temporal aspect leads to a rich set of optimization criteria for "shortest" walks. Extending and significantly broadening state-of-the-art work of Wu et al. [IEEE TKDE 2016], we provide an algorithm for computing optimal walks that is capable to deal with various optimization criteria and any linear combination of these. It runs in $O (|V| + |E| \log |E|)$ time where $|V|$ is the number of vertices and $|E|$ is the number of time edges. A central distinguishing factor to Wu et al.'s work is that our model allows to, motivated by real-world applications, respect waiting-time constraints for vertices, that is, the minimum and maximum waiting time allowed in intermediate vertices of a walk. Moreover, other than Wu et al. our algorithm also allows to search for walks that pass multiple subsequent edges in one time step, and it can optimize a richer set of optimization criteria. Our experimental studies indicate that our richer modeling can be achieved without significantly worsening the running time when compared to Wu et al.'s algorithms.

0
0
下载
预览
Top