中文

用于从 Web 抽取再技能与升技能选项的槽填充方法

信息检索 2022-07-12 v1

摘要

就业市场中的扰动,如科学技术进步、危机和竞争加剧,引发了再技能(reskilling)与升技能(upskilling)项目的激增。有关合适继续教育选项的信息分散于众多站点,使得搜索、比较和选择有用项目成为繁琐任务。因此,本文引入一个知识抽取系统,将再技能与升技能选项整合为单一知识图谱。该系统从 488 个不同提供商收集教育项目,并利用上下文抽取来识别相关内容并赋予上下文。随后,实体识别与实体链接方法借助领域本体定位诸如技能、职业和主题等相关实体。最后,槽填充根据上下文将实体整合进继续教育知识图谱的相应槽中。我们还引入一个德语黄金标准,包含 169 篇文档和超过 3800 条标注,用于基准测试必要的内容抽取、实体链接、实体识别和槽填充任务,并给出系统性能概览。

关键词

引用

@article{arxiv.2207.04862,
  title  = {Slot Filling for Extracting Reskilling and Upskilling Options from the Web},
  author = {Albert Weichselbraun and Roger Waldvogel and Andreas Fraefel and Alexander van Schie and Philipp Kuntschik},
  journal= {arXiv preprint arXiv:2207.04862},
  year   = {2022}
}

备注

Natural Language Processing and Information Systems (NLDB 2022). This preprint has not undergone any post-submission improvements or corrections. The Version of Record of this contribution is published in "27th International Conference on Applications of Natural Language to Information Systems (NLDB 2022), Valencia, Spain, June 15-17, 2022, Proceedings", and is available online at https://doi.org/10.1007/978-3-031-08473-7_25