A distantly supervised method for extracting spatio-temporal information from text
A distantly supervised method for extracting spatio-temporal information from text
复制标题
DOI：
10.1145/2996913.2996967
复制
发表时间：
2016-10
期刊：
影响因子：
--
通讯作者：
Seyed Iman Mirrezaei;Bruno Martins;I. Cruz
中科院分区：
文献类型：
--
作者：
Seyed Iman Mirrezaei;Bruno Martins;I. Cruz
本文描述了 Triplex-ST，一种用于从文本资源中收集时空信息的新型信息提取系统。 Triplex-ST 基于远程监督方法，该方法利用丰富的语言注释以及现有知识库中的信息。特别是，我们利用与时间和/或空间上下文相关的三元组（例如，可从 YAGO 知识库获得），以便推断出从以前未见过的句子中捕获新事实的模板。
This paper describes Triplex-ST, a novel information extraction system for collecting spatio-temporal information from textual resources. Triplex-ST is based on a distantly supervised approach, which leverages rich linguistic annotations together with information in existing knowledge bases. In particular, we leverage triples associated with temporal and/or spatial contexts, e.g., as available from the YAGO knowledge base, so as to infer templates that capture new facts from previously unseen sentences.