Named Entity Mention Detection Task

A Named Entity Mention Detection Task is a detection task where the named entity mentions must be detected in a linguistic item.

• AKA: Named Entity Detection Task, Named Entity Mention Segmentation Task, Named Entity Mention Segmentation.
• Context:
  • Input: Text Item.
    • optional: an NER Training Set.
    • optional: an Entity Database.
  • output: a Named Entity Mention Annotated Text Item.
  • It can be a part of the Named Entity Recognition Task.
  • It can be solved by a Named Entity Mention Detection System (that implements a Named Entity Mention Detection Algorithm).
  • It can be a Supervised NER Detection Task, if a NER Training Set is provided.
  • It can be a Dictionary-based NER Detection Task, if an Entity Database is provided.
• Example(s):
  • [math]\displaystyle{ f }[/math]("Jane Zhou went to São Paolo") ⇒ "[Jane Zhou] went to [São Paolo]".
  • …
• Counter-Example(s):
  • [math]\displaystyle{ f }[/math]("[Jane Zhou] went to [São Paolo]") ⇒ "[Jane Zhou]/PERSON went to [São Paolo]/LOCATION", a Named Entity Mention Classification Task.
  • [math]\displaystyle{ f }[/math]("Jane Zhou went to São Paolo") ⇒ "[Jane Zhou]/PERSON went to [São Paolo]/LOCATION", a Named Entity Mention Recognition Task.
• See: Entity Record Detection Task.

---

---

References

2007

• (Sutton & McCallum, 2007) ⇒ Charles Sutton, and Andrew McCallum. (2007). “An Introduction to Conditional Random Fields for Relational Learning.” In: (Getoor & Taskar, 2007).
  • The named-entity recognition task is, given a sentence, first to segment which words are part of entities, and then to classify each entity by type (person, organization, location, and so on). The challenge of this problem is that many named entities are too rare to appear even in a large training set, and therefore the system must identify them based only on context.

---