Improved hybrid semantic similarity algorithm for terminology application

Wei, Tong; Jia, Yangli; Zhang, Zhenling; Roche, Julien; Roche, Christophe

doi:10.1109/fskd.2016.7603439

Cited by 2 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of words semantic similarity calculation affect the progress of higher-level NLP tasks greatly. Establishing the appropriate semantic representation of natural language words and acquiring the similarity degree between words are the bases of the natural language processing task [2].…”

Section: Introductionmentioning

confidence: 99%

Measuring Semantic Similarity between Words Based on Multiple Relational Information

Duan

Wang

et al. 2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

The similarity of words extracted from the rich text relation network is the main way to calculate the semantic similarity. Complex relational information and text content in Wikipedia website, Community Question Answering and social network, provide abundant corpus for semantic similarity calculation. However, most typical research only focused on single relationship. In this paper, we propose a semantic similarity calculation model which integrates multiple relational information, and map multiple relationship to the same semantic space through learning representing matrix and semantic matrix to improve the accuracy of semantic similarity calculation. In experiments, we confirm that the semantic calculation method which integrates many kinds of relationships can improve the accuracy of semantic calculation, compared with other semantic calculation methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Measuring Semantic Similarity between Words Based on Multiple Relational Information

Duan

Wang

et al. 2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…The semantic correlation between D1 and D2 can be calculated in the following way which is provided in literature [9].…”

Section: + Fren Imentioning

confidence: 99%

Application of Intelligent Information Retrieval For Big Data Oriented Brain Science

Jia¹

2018

Proceedings of the 2018 3rd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 201

View full text Add to dashboard Cite

With the development of brain and cognition technology, the research on brain science is more and more thorough. And big data related to brain science is emerging. How to acquire and share these data in time is a very urgent problem in the development of brain science. Traditional information retrieval technology is often based on keyword matching, which does not investigate the semantics of retrieval words or search phrases. It has great defects in the field of brain science. And it is difficult to meet the retrieval requirements of brain science. The information retrieval about brain science has characteristics of real-time and retrieval methods diversification. So combining Ontology technology and professional needs, we proposed intelligent retrieval model based on ontology, which is suitable for the field of brain science. We improved semantic similarity algorithm more suitable for brain science information query. And the experimental results show that the retrieval of semantic similarity based on the improved algorithm can improve the recall and precision of information retrieval. BackgroundThe study of brain science become the research focus in the world. The United States, the EU, Japan have developed brain research program. New technology and new methods, new discoveries continue to emerge the brain science. In document [1],Innovation and new technology research means creation objective conditions to solve the human brain the mystery.In recent years, the theory of complex network, brain network visualization direction has achieved a breakthrough. It will play important significance for understanding the brain mechanisms and prevention of brain diseases. And it will promote the development of artificial intelligence systems. The progress of brain science is becoming more and more complex. At the same time, a large number of literature materials emerge in an endless stream. If we can index these resources in time and share them with the researchers in the most convenient way, we will greatly promote the progress of scientific research projects. Therefore, we need to design an efficient search system in the field of brain science to provide services for scientific research activities. The fundamental way to improve the quality of Brain Science information retrieval is to change disordered data into ordered knowledge, let computers understand the meaning of Brain Science information, and thus realize semantic retrieval. Research statusIn the field of modern brain science, information technology has become one of the ke y factors to promote the development of brain science. There are about more than 3290000 00 returned keywords in Google, including brain science, news and latest achievements. Fro m these data, we can see that at present, the information retrieval service in the field of fo

show abstract

Improved hybrid semantic similarity algorithm for terminology application

Cited by 2 publications

References 11 publications

Measuring Semantic Similarity between Words Based on Multiple Relational Information

Measuring Semantic Similarity between Words Based on Multiple Relational Information

Application of Intelligent Information Retrieval For Big Data Oriented Brain Science

Contact Info

Product

Resources

About