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
- EP ID EP89
- DOI 10.14196/sjr.v3i3.1259
- Views 602
- Downloads 39
Innervation and moan review process, from the perspective of law, and knowledge of management accounting
Innervations and Moan, the most important jurisprudential and legal issues, and the conflict between Sunnis and Shiites are the quality that most matters of inheritance and inheritance in Islamic law, the validity and in...
Investigating the effect of gas flow rate and amount of zinc oxide nanoparticles on the efficacy of photocatalytic oxida
Nitrogen oxides are one of the most important air pollutants in environment and industrythat due to the adverse health and environmental effects should be refined before discharging into the environment. The photocatal...
Justification of intellectual property rights, using game theory approach
The creation of intellectual rights protection is a challenging task, Since its creation. Protection of the rights and granted the exclusive right to use, Creates the social costs. In other words, Due to lack of access...
Experimental studies on structural load monitoring using piezoelectric transducer based electromechanical impedance meth
In general aerospace, civil and mechanical (ACM) structures are often subjected to some or the other forms of loading during their service life. It has been reported that about 75% of aerospace structures fail due to fat...
Immunoglobulin in colostrum and health of newborn Calves
Cow’s colostrum contains the basic alimentary constituents; fat, protein, carbohydrate, minerals and vitamins, in addition to immunoglobulin, biological factors, hormones and other biological particles. These constitue...