arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.06007cs.CL
收藏

利用表实体对的两跳远程监督进行关系抽取

Leveraging 2-hop Distant Supervision from Table Entity Pairs for Relation Extraction

The Ohio State University(俄亥俄州立大学)

Xiang Deng, Huan Sun

摘要:

远程监控(Distant Supervision,DS)已被广泛用于自动构造(噪声)标记数据以用于关系抽取(RE)。给定两个实体,远距离监督利用直接提到它们的句子来预测它们的语义关系。我们把这种策略称为1跳DS,不幸的是,它可能不适合于支持句子很少的长尾实体。在本文中,我们引入了一种新的策略,名为2跳DS,以提高远程监督RE,观察到存在大量的关系表在Web上包含共享共同关系的实体对。我们将这样的实体对称为彼此的锚,并收集所有提到给定目标实体对的锚实体对的句子,以帮助关系预测。我们在多示例学习范式中开发了一种新的神经RE方法REDS 2,该方法采用分层模型结构分别融合来自1跳DS和2跳DS的信息。在基准数据集上进行的大量实验结果表明,REDS2可以在不同的设置中始终优于各种基线。

英文摘要:

Distant supervision (DS) has been widely used to automatically construct (noisy) labeled data for relation extraction (RE). Given two entities, distant supervision exploits sentences that directly mention them for predicting their semantic relation. We refer to this strategy as 1-hop DS, which unfortunately may not work well for long-tail entities with few supporting sentences. In this paper, we introduce a new strategy named 2-hop DS to enhance distantly supervised RE, based on the observation that there exist a large number of relational tables on the Web which contain entity pairs that share common relations. We refer to such entity pairs as anchors for each other, and collect all sentences that mention the anchor entity pairs of a given target entity pair to help relation prediction. We develop a new neural RE method REDS2 in the multi-instance learning paradigm, which adopts a hierarchical model structure to fuse information respectively from 1-hop DS and 2-hop DS. Extensive experimental results on a benchmark dataset show that REDS2 can consistently outperform various baselines across different settings by a substantial margin.

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。

↑