Information Extraction Pattern

An Information Extraction Pattern is a Pattern that can identify and classify Information in Text.

• AKA: Wrapper, Extraction Rule, IE Wrapper, Information Extraction Wrapper.
• Context:
  • It can be a task output of an Information Extraction Task (to populate a Data Structure from the Data in an Artifact).
  • It can be a part of a Relation Recognition Model.
  • It can be:
    • a Person-made Information Extraction Pattern.
    • a Learned Information Extraction Pattern.
• Example(s):
  • a Lexico-Syntactic Pattern, such as:
    • “x such as y', ..., and y” ⇒ ISA(y',x). Hearst.
    • "A y is a type of x that ..” ⇒ ISA(y',x).
• See: Template Filling.

---

---

References

2007

• (Zaccak, 2007) ⇒ Gabriel Zaccak. (2007). “Wrapster : semi-automatic wrapper generation for semi-structured websites." Thesis (S.M.)--Massachusetts Institute of Technology.

1999

• (Soderland, 1999) ⇒ Stephen Soderland. (1999). “Learning Information Extraction Rules for Semi-Structured and Free Text.” In: Machine Learning, 44(1-3). doi:10.1023/A:1007562322031

1998

• (Freitag, 1998) ⇒ Dayne Freitag. (1998). “Information Extraction from HTML: Application of a General Machine Learning Approach.” In: Proceedings of AAAI/IAAI 1998.
  • Wrapper Induction Algorithm, Relation Mention Pattern.

1997

• (Kushmerick, 1997) ⇒ Nicholas Kushmerick, D. S. Weld, and R. B. Doorenhos. (1997). “Wrapper Induction for Information Extraction.” In: International Joint Conference on Artificial Intelligence (IJCAI 1997).
  • Wrapper Induction Algorithm, Relation Mention Pattern.

---