文本复述判别是一个重要的句子级语义理解应用.该文提出了一个轻量级的基于记忆单元的单层循环神经网络模型,并结合语义角色标注知识帮助进行英文文本复述判别.使用单层的循环网络模型减缓由于网络层数过多加重的梯度消失和梯度爆炸问题,易于训练;并且利用外部记忆单元和语义角色知识帮助存储两句话中不同层级的语义联系.该文模型在英文评测语料Microsoft Research Paraphrase Corpus测试集上 F值为84.3%.实验表明,语义角色标注知识确实可以帮助文本复述判别,并且轻量级模型达到了与同类多层次网络模型相近的效果.%Paraphrase identification is an important sentence semantic understanding task.In this paper,we present a light-weight memory based recurrent neural network with sematic role features for this issue.The proposed single layer recurrent network alleviates the gradient disappearance and gradient explosion which aggravate by multilayer neural networks.We employ semantic role features to describe the semantic relationships between two sentneces. On the test set of Microsoft Research Paraphrase Corpus,we achieve 84.3% in F1 score,which is competitive com-pared with multilayer neural network models.
展开▼
