| 融合门控机制的远程监督关系抽取方法 |
| |
| 引用本文： | 李兴亚,陈钰枫,徐金安,张玉洁.融合门控机制的远程监督关系抽取方法[J].北京大学学报(自然科学版),2020,56(1):39-44. |
| |
| 作者姓名： | 李兴亚 陈钰枫 徐金安 张玉洁 |
| |
| 作者单位： | 北京交通大学计算机与信息技术学院, 北京 100044 |
| |
| 基金项目： | 国家自然科学基金(61976016, 61473294, 61370130, 61876198)、北京市自然科学基金(4172047)和科学技术部国际科技合作计划(K11F100010)资助 |
| |
| 摘 要： | 提出一种融合门控机制的远程监督关系抽取方法。首先在词级别上自动选择正相关特征, 过滤与关系标签无关的词级别噪声; 然后在门控机制内引入软标签的思想, 弱化硬标签对噪声过滤的影响; 最后结合句子级别的噪声过滤, 提升模型的整体性能。在公开数据集上的实验结果表明, 相对于句子级别噪声过滤方法, 所提方法的性能有显著提高。
|
| 关 键 词： | 关系抽取 远程监督 门控机制 卷积神经网络 |
| 收稿时间： | 2019-05-23 |
Distant Supervision for Relation Extraction with Gate Mechanism |
| |
| LI Xingya,CHEN Yufeng,XU Jin’an,ZHANG Yujie.Distant Supervision for Relation Extraction with Gate Mechanism[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2020,56(1):39-44. |
| |
| Authors: | LI Xingya CHEN Yufeng XU Jin’an ZHANG Yujie |
| |
| Institution: | School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044 |
| |
| Abstract: | A piecewise convolutional neural network with gating mechanism is proposed, which would automatically filter positive correlation features at word-level. Moreover, the idea of soft-label is introduced to the gating mechanism to weaken the impact of hard labels on noise filtering. Combined with sentence-level noise filtering, the overall performance of the model is improved. The experimental results on the public dataset show that the proposed model has a significant improvement compared to the sentence-level noise filtering methods. |
| |
| Keywords: | relation extraction distant supervision gate mechanism convolutional neural network |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《北京大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《北京大学学报(自然科学版)》下载免费的PDF全文 |
