Data-Driven Entity Mention Linking Task

A Data-Driven Entity Mention Linking Task is a data-driven concept mention linking task that is an entity mention linking task.

• Context:
  • It can range from being a Supervised Entity Mention Linking Task to being an Unsupervised Entity Mention Linking Task.
  • It can be solved by a Data-Driven Entity Mention Linking System (that implements a data-driven entity mention linking algorithm).
  • …
• Counter-Example(s):
  • a Heuristic Entity Mention Linking Task.
  • a Data-Driven Relation Mention Linking Task.
• See: Data-Driven Reference Grounding Task, Entity Mention.

---

---

References

2014

• (Guo & Barbosa, 2014) ⇒ Zhaochen Guo, and Denilson Barbosa. (2014). “Robust Entity Linking via Random Walks.” In: Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management (CIKM 2014). doi:10.1145/2661829.2661887
  • QUOTE: Entity Linking is the task of assigning entities from a Knowledge Base to textual mentions of such entities in a document. State-of-the-art approaches rely on lexical and statistical features which are abundant for popular entities but sparse for unpopular ones, resulting in a clear bias towards popular entities and poor accuracy for less popular ones.

---