arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1703.03097cs.CLcs.AI
收藏

非法域名中的信息抽取

Information Extraction in Illicit Domains

Information Sciences Institute(信息科学研究所);USC Viterbi School of Engineering(南加州大学维特比工程学院)

Mayank Kejriwal, Pedro Szekely

摘要:

从人口贩运等非法领域中提取有用的实体和属性值是一个具有挑战性的问题,可能会产生广泛的社会影响。这些领域采用非典型的语言模型,有“长尾”,并遭受概念漂移的问题。在本文中,我们提出了一个轻量级的,功能不可知的信息抽取(IE)的范例专门为这些领域设计。我们的方法使用原始的,未标记的文本从初始语料库,和一些(12-120)种子注释每个域特定的属性,学习强大的IE模型未观察到的页面和网站。从经验上讲,我们证明了我们的方法可以在低监管和高监管环境中的五组注释的真实世界人口贩运数据集上超过18\%的F-测度,优于以特征为中心的条件随机场基线。我们还表明,我们的方法是证明强大的概念漂移,甚至可以有效地引导在串行计算环境。

英文摘要:

Extracting useful entities and attribute values from illicit domains such as human trafficking is a challenging problem with the potential for widespread social impact. Such domains employ atypical language models, have `long tails' and suffer from the problem of concept drift. In this paper, we propose a lightweight, feature-agnostic Information Extraction (IE) paradigm specifically designed for such domains. Our approach uses raw, unlabeled text from an initial corpus, and a few (12-120) seed annotations per domain-specific attribute, to learn robust IE models for unobserved pages and websites. Empirically, we demonstrate that our approach can outperform feature-centric Conditional Random Field baselines by over 18\% F-Measure on five annotated sets of real-world human trafficking datasets in both low-supervision and high-supervision settings. We also show that our approach is demonstrably robust to concept drift, and can be efficiently bootstrapped even in a serial computing environment.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑