Combining Local and Global Features Into a Siamese Network for Sentence Similarity
Combining Local and Global Features Into a Siamese Network for Sentence Similarity
复制标题
将局部和全局特征组合到连体网络中以实现句子相似性
DOI：
10.1109/access.2020.2988918
复制
发表时间：
2020-01-01
期刊：
影响因子：
3.9
通讯作者：
Zhao, Wenyu
中科院分区：
文献类型：
--
作者：
Li, Yulong;Zhou, Dong;Zhao, Wenyu
句子相似度被广泛应用于各种自然语言任务，如自然语言推理，释义识别和问答。然而，由于句子中词语的多样性和歧义性，使得句子相似度的度量变得困难。许多研究表明，使用句子的局部特征或全局特征将产生令人满意的句子表示，可以用来衡量句子相似度。局部特征反映了句子中相邻词之间的关系，而句子的序列信息通常由全局特征表示。然而，局部特征缺乏捕获序列信息的能力，而少量提取的全局特征不足以产生具有良好质量的句子表示。在本文中，我们提出了一个混合模型结合局部和全局特征到一个连体网络（HM-LGSN）的句子相似度计算。我们首先提出了一种新的卷积神经网络架构，称为组卷积神经网络，以提取最具代表性的局部特征（或单词语义特征）。然后，我们将这些新特征与预先训练的单词嵌入相结合，作为双向门控递归单元的输入，以提取句子的全局特征。最后，我们选择全局特征形成句子表示，并通过曼哈顿距离计算句子相似度。在SICK、MSRVID、STS-B数据集上的实验结果表明，该模型结合了局部特征和全局特征，显著提高了分类精度。
Sentence similarity is widely used in various natural language tasks such as natural language inference, paraphrase identification, and question answering. However, a variety of linguistic expressions and ambiguities of words in sentences make it difficult to measure sentence similarity. Many studies show that using local features or global features of a sentence will produce satisfactory sentence representations that can be utilized to measure sentence similarity. Local features reflect the relationships of adjacent words for each sentence and the sequence information of a sentence are usually expressed by global features. However, local features lack abilities to capture sequence information while a small amount of extracted global features is not enough to produce sentence representations with good qualities. In this paper, we propose A Hybrid Model combining Local and Global features into a Siamese Network (HM-LGSN) for sentence similarity calculation. We first propose a new convolution neural network architecture called group convolution neural network to extract the most representative local features (or word semantic features). Then we combine these new features with pre-trained embeddings of words as input to the Bidirectional Gated Recurrent Units to extract global features of sentences. Finally, we select the global features to form sentence representations and calculate sentence similarity through Manhattan distance. The experimental results on SICK, MSRVID, STS-B datasets show that the accuracy of our proposed model is significantly improved by combining local features and global features.