／var／logmarcus chiu

(Entity - Named Entity) Recognition／Identification／Chunking／Extraction／Resolution (NER)

Created on · Last Modified on

  • Entity Extraction (EE) - extracting entities from unstructured text
  • Entity Resolution refers to the task of finding all mentions of same real-world entity within a knowledge base or across multiple knowledge bases
  • Named Entity Recognition/Identification/Chunking/Extraction/Resolution
    • a type of Entity Extraction where entities are NAMES (i.e. proper nouns)
    • is a subtask of information extraction that seeks to locate and classify NAMED entities mentioned in unstructured text into predefined categories such as person names, organizations, locations, medical, etc

NER - 2 Steps/Tasks

  1. identify named entity’s boundary
  2. identify named entity’s category

NER - Example

Unstructured Text

Predefined Categories

The decision by the independent MP Andrew Wilkie to withdraw his support for the minority Labor government sounded dramatic but it should not further threaten its stability. When, after the 2010 election, Wilkie, Rob Oakeshott, Tony Windsor and the Greens agreed to support Labor, they gave just two guarantees: confidence and supply
  • date
  • person’s name
  • organization’s name

NER - Possible Feature Candidates

NER - Methods

sequence models such as:

Resources