Relation Extraction System

A Relation Extraction System is an information extraction system that can extract semantic relationships mentions from written documents.

• AKA: Semantic Relation Extraction System.
• Context:
  • It can range from a Unstructured Relation Extraction System, to being a Semi-Structured Relation Extraction System, to being Structured Relation Extraction System.
• Example(s):
  • a Dependency Relation Retraction System.
  • a Text-based Relation Extraction System.
  • a Relation Record Extraction System,
  • a RelEx System.
  • …
• Counter-Example(s):
  • a Information Retrieval System,
  • a Sentiment Analysis System,
  • a Named Entity Disambiguation System.
• See: Semantic Relation, Natural Language Processing System, Text Analytics, Semantic Analytics, Semantic Role Labeling, Semantic Parsing System.

---

---

References

2019

• (Wikipedia, 2019) ⇒ https://en.wikipedia.org/wiki/Relationship_extraction Retrieved:2019-10-13.
  • A relationship extraction task requires the detection and classification of semantic relationship mentions within a set of artifacts, typically from text or XML documents. The task is very similar to that of information extraction (IE), but IE additionally requires the removal of repeated relations (disambiguation) and generally refers to the extraction of many different relationships.

2008

• (Mandhani & Soderland, 2008) ⇒ Bhushan Mandhani, and Stephen Soderland. (2008). “Exploiting Hyponymy in Extracting Relations and Enhancing Ontologies.” In: IEEE Workshop on Natural Language Processing and Ontology Engineering.
  • Relation extraction systems typically rely on local lexical and syntactic features as evidence.

---