Information Extraction Using Semantic Relation Learning And Greedy Mapping
In this thesis, the work is motivated to learn the extraction of significant information from natural language text and specify the meanings of the content. The work of information extraction and mapping results in three main challenges. First, to propose a generic and flexible framework that integrat...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2016
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In this thesis, the work is motivated to learn the extraction of significant information from natural language text and specify the meanings of the content. The work of information extraction and mapping results in three main challenges. First, to propose a generic and flexible framework that integrates the information extraction and mapping processes into a workflow, such that it can be easily adapted to changes and requirements. Second, to define a representation model that is able to cater various structures with different features and characteristics. Third, to propose a learning algorithm for information extraction and mapping with minimum training effort. In order to address these challenges, a flexible information extraction and mapping framework, SemIE (Semantic-based Information Extraction and Mapping), is proposed. SemIE identifies significant relations from domain-specific text by utilising a semantic structure that describes the domain of discourse. |
|---|