arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1504.06580cs.CLcs.LGcs.NE
收藏

基于排序的卷积神经网络关系分类

Classifying Relations by Ranking with Convolutional Neural Networks

IBM Research(IBM研究院);IBM Watson(IBM沃森)

Cicero Nogueira dos Santos, Bing Xiang, Bowen Zhou

摘要:

关系分类是一个重要的语义处理任务,最先进的系统仍然依赖于昂贵的手工制作的功能。在这项工作中,我们使用一个卷积神经网络来处理关系分类任务,该网络通过排名来执行分类(CR-CNN)。我们提出了一个新的成对排序损失函数,可以很容易地减少人工类的影响。我们使用SemEval-2010 Task 8数据集进行实验,该数据集是为对句子中标记的两个名词之间的关系进行分类而设计的。使用CRCNN,我们在这个数据集上的表现优于最先进的技术,并在不使用任何昂贵的手工特征的情况下实现了84.1的F1。此外,我们的实验结果表明:(1)我们的方法比CNN后面跟着softmax分类器更有效;(2)省略人工类Other的表示提高了精度和召回率;(3)如果我们只考虑两个目标名词之间的文本,仅使用词嵌入作为输入特征就足以实现最先进的结果。

英文摘要:

Relation classification is an important semantic processing task for which state-ofthe-art systems still rely on costly handcrafted features. In this work we tackle the relation classification task using a convolutional neural network that performs classification by ranking (CR-CNN). We propose a new pairwise ranking loss function that makes it easy to reduce the impact of artificial classes. We perform experiments using the the SemEval-2010 Task 8 dataset, which is designed for the task of classifying the relationship between two nominals marked in a sentence. Using CRCNN, we outperform the state-of-the-art for this dataset and achieve a F1 of 84.1 without using any costly handcrafted features. Additionally, our experimental results show that: (1) our approach is more effective than CNN followed by a softmax classifier; (2) omitting the representation of the artificial class Other improves both precision and recall; and (3) using only word embeddings as input features is enough to achieve state-of-the-art results if we consider only the text between the two target nominals.

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。

↑