Efficient calculation of sentence semantic similarity: a proposed scheme based on machine learning approaches and NLP te

Journal Title: Scientific Journal of Review - Year 2014, Vol 3, Issue 3

Abstract

Sentence semantic similarity plays a crucial role in a variety of applications such as Machine Translation, Information Retrieval, Question Answering and Multi-document Summarization. Considering the variability of natural language expression, sentence semantic similarity detection is not a trivial task. This paper tries to make use of Natural Language Processing (NLP) as well as machine learning techniques in order to propose a scheme for sentence semantic similarity. In the first part of the proposed scheme, i.e., the NLP section, different sets of linguistic features including string-based, semantic-based, Named Entity-based and syntax-based features are extracted. In the second part, machine learning algorithms are used to construct classification models on the extracted set of features. Experimental results in the first part indicate that extracted features are valid for sentence semantic similarity. Moreover, by comparing the performance of different classification algorithms in the second part, KNN seems to be the most successful algorithm. Overall, experimental results indicate that the proposed approach can be used to improve the performance of sentence semantic similarity detection especially in terms of accuracy.

Authors and Affiliations

M. Roostaee| Department of Computer Science and Engineering and IT, School of Electrical Engineering and Computer, Shiraz, Iran., S. M. Fakhrahmad| Department of Computer Science and Engineering and IT, School of Electrical Engineering and Computer, Shiraz, Iran., M. H. Sadreddini*| Department of Computer Science and Engineering and IT, School of Electrical Engineering and Computer, Shiraz, Iran., A. Khalili| Department of Computer Science and Engineering and IT, School of Electrical Engineering and Computer, Shiraz, Iran.

Keywords

Related Articles

The link between utopia and nostalgia and its reflection on literature

Nostalgia technically refers to human feeling of missing the past and those things s/he has lost. Different factors contribute to this feeling, including the human's social and political situation and, in general, his/he...

Health administrative and administrative identification in Iran

Today, the official health as an important approach in dealing with corruption experts have noted, on this article the concept identification of organizational culture and organizational social capital, their ways...

Modeling and simulation of fungi transport in waste dump site in Obioakpor, rivers Stater of Nigeria

Modeling and simulation of fungi transport in waste dump site has been evaluated. Mathematical model were developed considering all the variables in the system that influence transport process of fungi to ground water aq...

Engendered climate change impact and response knowledge, and its implication for adaptation, vulnerability and resilienc

Gender is a socio-economic variable which can be used to analyze adaptation, vulnerability and resilience of people against climate change and variability in local communities in Sub Saharan Africa (Assan, 2014). Clima...

Types of government - size of government

The state is one of the issues or phenomena that human life is full of it and can be traced to the aftermath Search everywhere; some scholars have suggested several indicators of the size of government, each of the indic...

Download PDF file
  • EP ID EP89
  • DOI 10.14196/sjr.v3i3.1259
  • Views 636
  • Downloads 39

How To Cite

M. Roostaee, S. M. Fakhrahmad, M. H. Sadreddini*, A. Khalili (2014). Efficient calculation of sentence semantic similarity: a proposed scheme based on machine learning approaches and NLP te. Scientific Journal of Review, 3(3), 94-106. https://europub.co.uk/articles/-A-89