Dissertation > Excellent graduate degree dissertation topics show

Social networking applications for relation extraction research

Author: JiangChaoNan
Tutor: DingZuoChun
School: Nanjing University of Technology and Engineering
Course: Information Science
Keywords: Named Entity Recognition Role Labeling Relation extraction Ontology of social relations SWRL rules Jess Implicit Relational Mining
CLC: G350
Type: Master's thesis
Year: 2010
Downloads: 245
Quote: 2
Read: Download Dissertation


Since search engines appeared so far , blowing a lot of information , but most of them are duplicate information . Search engine returns too many results but still difficult to find useful information. If there is a way to effectively filter search results can only extract the key information that people need , and in the network diagram form , rather than merely presented in the form of text , then the efficiency of access to information and will certainly greatly increased. Based on this, the field of social networks for relationships between named entities extraction conducted in-depth research , try to build a social network for the field of social relations body contains two or more named entities extracted sentences corresponding words as a description of the relationship between the entities . It also defines a set of SWRL rules and Jess inference engine combines the implicit ontology of social relations were tapped. In the named entity recognition task , the paper focuses names and organization names are identified , drawing on the idea of ??semantic role labeling , using the Viterbi algorithm, automatic annotation of sentence fragments in each sub-word names or organization names represent different roles , while according to the names and organization names into words characteristics , summed qualifying word formation rules for pattern matching in order to obtain the final recognition results. This corpus has been open to the real test , the experimental results show that this method is higher than recall accuracy rate close to 70%. This result proves the effectiveness of the method . In relation extraction task, this comprehensive ontology engineering into the seven-step method and the iterative method , to build a social network for field applied to the Internet on corporate social relationships within the industry body . SWRL also designed a series of rules to be introduced in conjunction with the social body Jess rule inference engine , try the concept of strict logical relationship ontology reasoning to dig out the implicit social relationships between entities . Finally get ( Entity Relationship Entity ) triples the relationship between the library and deposited greatly refined the information content , improve the efficiency of access to information .

Related Dissertations

  1. The Research for Named Entity Recognition and Relation Extraction in Text,TP391.1
  2. Ontology-based medicine named entity recognition technology research,TP391.1
  3. CRF -based named joint extraction of entities and relationships,TP391.4
  4. Click data and search results based on fragments excavated named entities,TP391.3
  5. Based on self-learning social relation extraction research,TP391.1
  6. Research of Protein-Protein Interaction Extraction Based on Rich Feature and Multiple Kernels Learning,Q51
  7. A Conceptual Query Based Multi-Document Summarization in Biomedical Domain,TP391.1
  8. Chinese named entity recognition and disambiguation of,TP391.1
  9. Study on Chinese Name Entity Recognition and Some Related Issues,TP391.41
  10. Based on Maximum Entropy Model Research on extracting Chinese entity relation,TP391.1
  11. Research on Construct of Domain Ontology Based on Hierarchical Demand and Method of Semantic Annotation,TP391.1
  12. The Research of Conditional Random Fields Based Chinese Named Entity Recognition,TP391.4
  13. Chinese Named Entity Recognition Based on Conditional Random Fields,TP391.43
  14. The Study of POI Abbreviations Dictionary in the Filed of Location Search,TP391.3
  15. Domain adaptive Chinese entity relation extraction research,TP391.1
  16. Research on Product Named Entity Recognition and Normalization,TP391.1
  17. English two-way time numbers and quantifiers identification and translation technology,TP391.2
  18. Semantic Role Labeling integration strategy research,TP391.1
  19. Research on Comparative Opinion Mining Based on Web,TP391.1
  20. Research on Machine Learning-based Protein-Protein Interaction Extraction,Q51-3
  21. Chinese Dependency-based Semantic Role Labeling,TP391.1

CLC: > Culture, science,education, sports > Science,scientific research > Information science, intelligence > Information Science
© 2012 www.DissertationTopic.Net  Mobile