Earticle

초록

영어

Combined with the issue of single direction of the solution of the existing sentence similarity algorithms, a Chinese sentence similarity computational model based on multi-features combination was proposed. The approach combines word overlap similarity, word order similarity, dependency relationship similarity, semantic similarity, structure similarity, sentence similarity, and keyword distance similarity to calculate the similarity between sentences, using the weight to describe the contribution of each feature of the sentence, and then gets a better experiment result. Experimental results shows that this approach can fully describe the features of the sentence, therefore can improve the sentence similarity computation accuracy.

목차

Abstract
 1. Introduction
 2. Related Works
 3. Sentence Similarity Computational Model
  3.1. Word Overlap Similarity Measure
  3.2. Word Order Similarity Measure
  3.3. Dependency Relationship Similarity Measure [6]
  3.4. Semantic Similarity Measure
  3.5. Structure Similarity Measure
  3.6. Sentence Length Similarity Measure [15]
  3.7. Keyword Distance Similarity Measure
  3.8. Sentence Similarity Measure Based on Multi-Features
 4. Experiments and Analysis
  4.1. MSRP Data Set
  4.2. Experimental Results
 5. Conclusion
 References

키워드

저자

• Peiying Zhang [ College of Computer & Communication Engineering, China University of Petroleum (East China), Qingdao shandong, China ]
• Qiuming Li [ College of Computer & Communication Engineering, China University of Petroleum (East China), Qingdao shandong, China ]
• Huayu Li [ College of Computer & Communication Engineering, China University of Petroleum (East China), Qingdao shandong, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Database Theory and Application

• 간기

  격월간

• pISSN

  2005-4270

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605