Loading...

Semantic Relation Extraction from Text Corpus Using Data Mining Methods

Lashakri, Mahdi | 2011

534 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 41302 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Abolhassani, Hassan
  7. Abstract:
  8. Semantic relation extraction is one of the challenging information extraction’s steps. The main task of relation extraction is finding of relationships in text corpus using Machine Learning methods. There are plenty of usage for relation extraction such as providing information for Question Answering systems, protein interaction detection in biomedical corpora and ontology population. There are many research take placed in this area in which relation extraction task is defined as a classification problem and in most of them, this problem is solved by SVM method. Results of recent research imply that current state of relation extraction methods are far from appropriate state that is applicable practically. In this study I have tried to propose a new method based on sequential pattern mining. The main idea of this study is finding of sequential patterns in sentences to form a model for every relation type and then classify new relations based on those models. Actually the main idea of this work is use of sequences that exists among words in a sentence. To find sequential patterns, PrefixSpan and CloSpan algorithms are used and output of these algorithms (patterns) for each relation type is used as a model. To identify a new sentence’s label, we should determine that how many of patterns of each class are belonged to this new sentence. After that, the relation that has more patterns in that sentence is the label of that sentence. The results of this work show remarkable performance and improvement in both precision and recall
  9. Keywords:
  10. Information Extraction ; Relation Extraction ; Data Mining ; Sequential Patterns Mining

 Digital Object List

 Bookmark

No TOC