Weakly-Supervised Algorithm

A Weakly-Supervised Algorithm is a semi-supervised algorithm that can solve a weakly-supervised learning task.

• AKA: Indirect Supervision.
• Example(s):
  • a Bootstrapped Learning Algorithm, such as Snowball Algorithm.
  • …
• Counter-Example(s):
  • a Large Labeled Dataset Semi-Supervised Algorithm.
  • a Self-Training Algorithm.
  • a Co-Training Algorithm.
• See: Supervised Learning.

---

---

References

2006

• (Klementiev & Roth, 2006) ⇒ Alexandre Klementiev, and Dan Roth. (2006). “Weakly Supervised Named Entity Transliteration and Discovery from Multilingual Comparable Corpora.” In: Proceedings of the 21st International Conference on Computational Linguistics and the 44th Annual Meeting of the Association for Computational Linguistics (ACL 2006). doi:10.3115/1220175.1220278

---