Hierarchical Attention Model for Acquiring Relationships Among Sentences
Hierarchical Attention Model for Acquiring Relationships Among Sentences
复制标题
DOI：
10.1109/isai-nlp48611.2019.9045713
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Hiroki Teranishi;M. Okada;N. Mori
中科院分区：
文献类型：
--
作者：
Hiroki Teranishi;M. Okada;N. Mori
在本文中，我们提出了一种用于摘要的分层注意力模型。通常，句子之间存在相互关系，在进行摘要时考虑这些关系是很重要的。我们提出的模型能够从由多个句子组成的文档中生成每个句子向量，并通过合并操作从这些向量中获取句子之间的关系。作为获取关系的操作，我们使用了自注意力机制和门控卷积神经网络。据报道，这些操作能够获取单词之间的依存关系，并且自注意力机制尤其强大。因此，我们采用这些操作，期望它们在句子中能起到同样的作用。我们使用日本新闻文章进行了标题生成实验。我们通过Rouge评估了我们提出的模型的性能，并对句子之间的关系进行了可视化。
In this paper, we propose a hierarchical attention model for summarization. Normally, sentences have relations among another sentence and it is important to consider these relations in summarizing. Our proposed model can make each sentence vectors from document composed of multi sentences and get relations among sentences from these vectors by the incorporated operation. As an operation of taking relations, we use self-attention and gated convolutional neural network. It has been reported that these operations can get dependencies among words, and self-attention is particularly powerful. Therefore we adopted these operations expecting the same work in sentences. We conducted an experiment of title generation by using Japanese news articles. We evaluated the performance of our proposed model by Rouge and visualized the relations among sentences.