A Sentence Similarity Estimation Method Based on Improved Siamese Network - Journal of Intelligent Learning Systems and Applications

JILSA > Vol.10 No.4, November 2018

A Sentence Similarity Estimation Method Based on Improved Siamese Network ()

HTML XML

Download as PDF (Size: 924KB) PP. 121-134

DOI: 10.4236/jilsa.2018.104008 1,754 Downloads 4,724 Views Citations

Author(s)

Ziming Chi^*, Bingyan Zhang^*

Affiliation(s)

College of Artificial Intelligence, Nankai University, Tianjin, China.

ABSTRACT

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.

KEYWORDS

Share and Cite:

Chi, Z. and Zhang, B. (2018) A Sentence Similarity Estimation Method Based on Improved Siamese Network. Journal of Intelligent Learning Systems and Applications, 10, 121-134. doi: 10.4236/jilsa.2018.104008.

Journals Menu

Follow SCIRP

	+1 323-425-8868
	customer@scirp.org
	+86 18163351462(WhatsApp)
	1655362766

	Paper Publishing WeChat

Journals Menu

Home

About SCIRP

Service

Policies