A Sentence Similarity Estimation Method Based on Improved Siamese Network

• 作者: Bingyan Zhang Ziming Chi
• 来源期刊: 智能学习系统与应用(英文)
• 学科: 工学
• 关键词: SENTENCE SIMILARITY SENTENCE Modeling SIMILARITY Measurement ATTENTION Mechanism Fully-Connected Layer DISORDER SENTENCE DATASET
• 年，卷（期）: 2018,（4）
• 页码范围: 121-134
• 页数: 14页
• 分类号: TP39

摘要

In this paper we employ an improved Siamese neural network to assess the semantic similarity between sentences. Our model implements the function of inputting two sentences to obtain the similarity score. We design our model based on the Siamese network using deep Long Short-Term Memory (LSTM) Network. And we add the special attention mechanism to let the model give different words different attention while modeling sentences. The fully-connected layer is proposed to measure the complex sentence representations. Our results show that the accuracy is better than the baseline in 2016. Furthermore, it is showed that the model has the ability to model the sequence order, distribute reasonable attention and extract meanings of a sentence in different dimensions.