CORA Citation Benchmark Task

A CORA Citation Benchmark Task is a Benchmark Task associated with the CORA Citation Search Engine.

• AKA: CORA Benchmark Task.
• Context:
  • It includes:
    • the CORA Citation Matching Benchmark Task.
    • the CORA Research Paper Classification Benchmark Task.
    • the CORA Information Extraction Benchmark Task.
• See: Citation.

---

---

References

• http://www.cs.umass.edu/~mccallum/code-data.html
  • Cora Citation Matching [reference matching, object correspondence]
    • Text of citations hand-clustered into groups referring to the same paper.
    • http://www.cs.umass.edu/~mccallum/data/cora-refs.tar.gz
  • Cora Research Paper Classification [relational document classification]
    • Research papers classified into a topic hierarchy with 73 leaves. We call this a relational data set, because the citations provide relations among papers.
    • http://www.cs.umass.edu/~mccallum/data/cora-classify.tar.gz
  • Cora Information Extraction [information extraction]
    • Research paper headers and citations, with labeled segments for authors, title, institutions, venue, date, page numbers and several other fields.
    • http://www.cs.umass.edu/~mccallum/data/cora-ie.tar.gz

---