Loading...
Please wait, while we are loading the content...
Similar Documents
A Hybrid Approach for Semantic Structure Annotating of Text
| Content Provider | CiteSeerX |
|---|---|
| Abstract | Facing the challenges of annotating naturally occur-ring text into semantic structured form for automatically information extracting, current Semantic Role Labeling (SRL) systems have been focusing on semantic predicate-argument structure. Based on the Concept Description Lan-guage for Natural Language (CDL.nl) which aims to de-scribe the concept structure of text by a set of pre-defined semantic relations, we develop a parser to add a new layer of semantic annotation of natural language sentences. The parsing task is a relation extraction process with two steps: relation detection and relation classification. We put for-ward a hybrid approach with different methods for two steps: firstly, based on dependency analysis, a rule-based method is presented to detect all entity pairs between each pair there exits a relationship; secondly, we use a feature-based method to assign CDL.nl relation to each detected entity pair with Support Vector Machine. We report our preliminary results on our manual dataset annotated with CDL.nl relations. 1. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Hybrid Approach Semantic Structure Annotating Entity Pair Pre-defined Semantic Relation Natural Language Sentence Feature-based Method Relation Detection Current Semantic Role Labeling Occur-ring Text Different Method Relation Extraction Process Manual Dataset Concept Structure New Layer Concept Description Lan-guage Natural Language Semantic Annotation Nl Relation Relation Classification Information Extracting Rule-based Method Parsing Task Semantic Predicate-argument Structure Support Vector Machine Preliminary Result Dependency Analysis Semantic Structured Form |
| Content Type | Text |