Leveraging 2-hop Distant Supervision from Table Entity Pairs for Relation Extraction
Leveraging 2-hop Distant Supervision from Table Entity Pairs for Relation Extraction
复制标题
DOI：
10.18653/v1/d19-1039
复制
发表时间：
2019-09
期刊：
影响因子：
--
通讯作者：
Xiang Deng;Huan Sun
中科院分区：
文献类型：
--
作者：
Xiang Deng;Huan Sun
远程监督(DS)已被广泛用于自动构造(含噪声)标记数据以用于关系提取(RE)。在给定两个实体的情况下，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。我们将这种策略称为1跳DS，不幸的是，这种策略可能不适用于支持语句很少的长尾实体。基于Web上存在大量包含公共关系的实体对的关系表，本文提出了一种新的策略--2-Hop DS来增强远程监督逆向工程。我们将这些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，以帮助进行关系预测。在多示例学习模式下，我们提出了一种新的神经RE方法REDS2，它采用分层模型结构来分别融合来自1跳DS和2跳DS的信息。在基准数据集上的广泛实验结果表明，REDS2在不同的设置下可以一致地远远超过不同的基线。
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.