Accurate Information Extraction from Research Papers using Conditional Random Fields

With the increasing use of research paper search engines, such as CiteSeer, for both literature search and hiring decisions, the accuracy of such systems is of paramount importance. This paper employs Conditional Random Fields (CRFs) for the task of extracting various common fields from the headers and citation of research papers. The basic theory of CRFs is becoming well-understood, but best-practices for applying them to real-world data requires additional exploration. This paper makes an empirical exploration of several factors, including variations on Gaussian, exponential and hyperbolic

• Type: Conference
• Year: 2004
• Where: NAACL
• Authors: Fuchun Peng, Andrew McCallum
• Keywords: Conditional Random Fields, NAACL 2004, NAACL 2007, Research Paper Search, Research Papers