当前位置: X-MOL 学术Inf. Process. Manag. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A gated piecewise CNN with entity-aware enhancement for distantly supervised relation extraction
Information Processing & Management ( IF 8.6 ) Pub Date : 2020-08-18 , DOI: 10.1016/j.ipm.2020.102373
Haixu Wen , Xinhua Zhu , Lanfang Zhang , Fei Li

The piecewise convolutional neural network (PCNN) is an important method for distant supervision relation extraction. However, the existing methods based on the PCNN still have the following shortcomings: these methods lack the consideration of the impacts of entity pairs and the sentence context on word encoding and do not distinguish the different contributions of the three segments in PCNN to relation classification. To solve these problems, we propose a novel gated piecewise CNN with entity-aware enhancement for distantly supervised relation extraction. First, we use a multi-head self-attention mechanism to combine the word embedding with the head/tail entity embedding and relative position embedding to generate an entity-aware enhanced word representation, which is capable of capturing the semantic dependency between each word and entity pair. Then we introduce a global gate to combine each entity-aware enhanced word representation with their average in the input sentence to form the final word representation of the PCNN input. Moreover, to determine the key segments where the most important information for relation classification appears, we design another gate mechanism to assign a different weight to each sentence segment to highlight the effects of key segments on the PCNN. Experiments on New York Times dataset demonstrate that our model significantly outperforms most of the state-of-the-art models.



中文翻译:

具有实体感知增强功能的门控分段CNN,用于远程监督的关系提取

分段卷积神经网络(PCNN)是一种用于远程监管关系提取的重要方法。但是,基于PCNN的现有方法仍然存在以下缺点:这些方法没有考虑实体对和句子上下文对单词编码的影响,并且没有区分PCNN中的三个部分对关系分类的不同贡献。为了解决这些问题,我们提出了一种新的带有实体感知增强功能的门控分段CNN,用于远程监督关系提取。首先,我们使用多头自我注意机制,将单词嵌入与头/尾实体嵌入和相对位置嵌入相结合,以生成可感知实体的增强型单词表示,该表示能够捕获每个单词与实体对。然后,我们引入一个全局门,将每个实体感知的增强词表示形式与输入句子中的平均值相结合,以形成PCNN输入的最终词表示形式。此外,为了确定其中最重要的关系分类信息出现的关键片段,我们设计了另一种门机制,为每个句子片段分配不同的权重,以突出显示关键片段对PCNN的影响。在《纽约时报》数据集上进行的实验表明,我们的模型大大优于大多数最新模型。为了确定最重要的关系分类信息所在的关键片段,我们设计了另一种门机制,为每个句子片段分配不同的权重,以突出显示关键片段对PCNN的影响。《纽约时报》数据集上的实验表明,我们的模型大大优于大多数最新模型。为了确定最重要的关系分类信息所在的关键片段,我们设计了另一种门机制,为每个句子片段分配不同的权重,以突出显示关键片段对PCNN的影响。在《纽约时报》数据集上进行的实验表明,我们的模型大大优于大多数最新模型。

更新日期:2020-08-18
down
wechat
bug